{"id":"f349ecc2-eb51-42c1-b541-f4c25a3aaadf","entityType":"agent","slug":"clawhub-athola-nm-leyline-additive-bias-defense","name":"additive-bias-defense","canonicalUrl":"https://www.xpersona.co/agent/clawhub-athola-nm-leyline-additive-bias-defense","canonicalPath":"/agent/clawhub-athola-nm-leyline-additive-bias-defense","generatedAt":"2026-10-14T10:43:54.923Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T21:10:58.017Z","emptyReason":null},"description":"Inverts burden of proof for code additions Skill: additive-bias-defense Owner: athola Summary: Inverts burden of proof for code additions Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:13:54.522Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:35:07.810Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:51:50.805Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:00:47.850Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16:19:23.613Z | user Release v1.9.1","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 992 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-leyline-additive-bias-defense","sourceUrl":"https://clawhub.ai/athola/nm-leyline-additive-bias-defense","homepage":"https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/athola/nm-leyline-additive-bias-defense","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Inverts burden of proof for code additions Skill: additive-bias-defense Owner: athola Summary: Inverts burden of proof for code additions Tags: latest:1.9.19 Ve"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:10:58.017Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:10:58.017Z","emptyReason":null},"stars":null,"forks":null,"downloads":992,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.9.19","tractionLabel":"992 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:10:58.005Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T21:10:58.017Z","lastCrawledAt":"2026-10-11T21:10:58.005Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T21:10:58.005Z","lastVerifiedAt":null,"highlights":[{"version":"1.9.19","createdAt":"2026-08-26T13:13:54.522Z","changelog":"Release v1.9.19","fileCount":3,"zipByteSize":3703},{"version":"1.9.17","createdAt":"2026-07-30T05:35:07.810Z","changelog":"Release v1.9.17","fileCount":3,"zipByteSize":3679},{"version":"1.9.16","createdAt":"2026-07-14T19:51:50.805Z","changelog":"Release v1.9.16","fileCount":3,"zipByteSize":3632},{"version":"1.9.14","createdAt":"2026-06-30T18:00:47.850Z","changelog":"Release v1.9.14","fileCount":3,"zipByteSize":3735},{"version":"1.9.13","createdAt":"2026-06-27T16:19:23.613Z","changelog":"Release v1.9.13","fileCount":3,"zipByteSize":3690},{"version":"1.9.12","createdAt":"2026-06-19T03:13:39.949Z","changelog":"Release v1.9.12","fileCount":3,"zipByteSize":3790},{"version":"1.0.0","createdAt":"2026-06-18T14:08:58.690Z","changelog":"- Initial release of the additive-bias-defense skill, ported from claude-night-market/leyline. - Establishes a defense against unnecessary code additions by inverting the burden of proof: all new additions must be explicitly justified. - Introduces a set of five scrutiny questions and six anti-pattern signals to evaluate proposed changes. - Defines a clear burden-of-proof verdict system: justified, needs_evidence, or unjustified. - Outlines integration expectations for review-oriented skills and references related supporting skills. - Promotes the subtraction principle: consider removals or simpler alternatives before accepting additions.","fileCount":3,"zipByteSize":3664}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-leyline-additive-bias-defense","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-14T10:43:54.922Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-leyline-additive-bias-defense/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T21:10:58.017Z","emptyReason":null},"readme":"Skill: additive-bias-defense\n\nOwner: athola\n\nSummary: Inverts burden of proof for code additions\n\nTags: latest:1.9.19\n\nVersion history:\n\nv1.9.19 | 2026-08-26T13:13:54.522Z | user\n\nRelease v1.9.19\n\nv1.9.17 | 2026-07-30T05:35:07.810Z | user\n\nRelease v1.9.17\n\nv1.9.16 | 2026-07-14T19:51:50.805Z | user\n\nRelease v1.9.16\n\nv1.9.14 | 2026-06-30T18:00:47.850Z | user\n\nRelease v1.9.14\n\nv1.9.13 | 2026-06-27T16:19:23.613Z | user\n\nRelease v1.9.13\n\nv1.9.12 | 2026-06-19T03:13:39.949Z | user\n\nRelease v1.9.12\n\nv1.0.0 | 2026-06-18T14:08:58.690Z | auto\n\n- Initial release of the additive-bias-defense skill, ported from claude-night-market/leyline.\n- Establishes a defense against unnecessary code additions by inverting the burden of proof: all new additions must be explicitly justified.\n- Introduces a set of five scrutiny questions and six anti-pattern signals to evaluate proposed changes.\n- Defines a clear burden-of-proof verdict system: justified, needs_evidence, or unjustified.\n- Outlines integration expectations for review-oriented skills and references related supporting skills.\n- Promotes the subtraction principle: consider removals or simpler alternatives before accepting additions.\n\nArchive index:\n\nArchive v1.9.19: 3 files, 3703 bytes\n\nFiles: skill-card.md (1983b), SKILL.md (4479b), _meta.json (152b)\n\nFile v1.9.19:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.9.19:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.19\",\n \"publishedAt\": 1787750034522\n}\n\nFile v1.9.19:skill-card.md\n\n## Description:\n\nInverts burden of proof for code additions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[athola](https://clawhub.ai/user/athola)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering agents use this skill during reviews, refactors, planning, and cleanup work to challenge proposed additions with evidence-focused scrutiny questions and anti-pattern checks.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The broad triggers and strong burden-of-proof framing may make an agent push back more often than desired in general engineering discussions.\n\nMitigation: Apply the skill primarily during reviews, refactors, planning, and cleanup work where evidence-based scrutiny of additions is desired.\n\nRisk: A justified addition may be delayed if its rationale or consequence is not documented clearly.\n\nMitigation: Ask for concise evidence explaining why the addition is needed and what breaks without it before accepting a needs_evidence or unjustified verdict.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense)\n- [OpenClaw homepage](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Text]\n\n**Output Format:** [Markdown guidance with scrutiny questions, anti-pattern checks, and verdict labels]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [No code execution, persistence, credential access, or hidden data handling reported by security evidence.]\n\n## Skill Version(s):\n\n1.9.19 (source: ClawHub release metadata; artifact frontmatter reports 1.9.8)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.9.17: 3 files, 3679 bytes\n\nFiles: skill-card.md (1964b), SKILL.md (4479b), _meta.json (152b)\n\nFile v1.9.17:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.9.17:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.17\",\n \"publishedAt\": 1785389707810\n}\n\nFile v1.9.17:skill-card.md\n\n## Description:
\nInverts burden of proof for code additions
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and code reviewers use this guidance skill to challenge proposed code, file, configuration, and abstraction additions before accepting them into a task or review.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Broad activation terms can make an agent challenge additions more often than intended.
\nMitigation: Use the skill when stricter review or refactor scrutiny is desired, and tie challenges to the active task requirements.
\nRisk: A guidance-only verdict can reject useful work if the need has not been documented yet.
\nMitigation: Provide concrete evidence, reproduction steps, or requirement links before treating an addition as justified.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense)
\n- [Leyline plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)
\n\n\n## Skill Output:
\n**Output Type(s):** [Guidance, Analysis, Markdown]
\n**Output Format:** [Markdown guidance with scrutiny questions, anti-pattern checks, and burden-of-proof verdicts]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Guidance-only; no tools, credentials, persistence, or privileged authority requested.]
\n\n## Skill Version(s):
\n1.9.17 (source: server release metadata; artifact frontmatter lists 1.9.8)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.9.16: 3 files, 3632 bytes\n\nFiles: skill-card.md (1966b), SKILL.md (4479b), _meta.json (152b)\n\nFile v1.9.16:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.9.16:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.16\",\n \"publishedAt\": 1784058710805\n}\n\nFile v1.9.16:skill-card.md\n\n## Description:
\nInverts burden of proof for code additions.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and code reviewers use this guidance skill to challenge proposed code, file, abstraction, error-handling, and configuration additions before accepting them.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill may activate during common PR review or refactor-planning conversations because of broad trigger wording.
\nMitigation: Review the trigger wording and invoke the skill explicitly when tighter control is needed.
\nRisk: Guidance-oriented outputs may introduce incorrect or misleading review conclusions if accepted without review.
\nMitigation: Review and scan the skill before deployment, and treat its verdicts as review guidance rather than automatic enforcement.
\n\n\n## Reference(s):
\n- [Leyline plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)
\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown, text]
\n**Output Format:** [Markdown guidance with scrutiny questions, anti-pattern checks, and burden-of-proof verdicts]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Broad trigger wording may activate during common PR review or refactor-planning conversations.]
\n\n## Skill Version(s):
\n1.9.16 (source: ClawHub release metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.9.14: 3 files, 3735 bytes\n\nFiles: skill-card.md (2203b), SKILL.md (4479b), _meta.json (152b)\n\nFile v1.9.14:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.9.14:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.14\",\n \"publishedAt\": 1782842447850\n}\n\nFile v1.9.14:skill-card.md\n\n## Description:
\nInverts burden of proof for code additions.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineering teams use this skill to review proposed code, file, abstraction, error-handling, and configuration additions for necessity, priority alignment, simplicity, and evidence.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Broad trigger wording may cause the skill to activate in common code-review or refactor discussions and steer the agent toward a stricter review posture.
\nMitigation: Invoke the skill explicitly or narrow trigger wording when teams want tighter control over when this review posture is applied.
\nRisk: The skill is advisory and may challenge useful additions if reviewers apply its burden-of-proof checks without project context.
\nMitigation: Review the generated scrutiny and verdicts against the active task, requirements, and evidence before accepting or removing proposed changes.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense)
\n- [ClawHub publisher profile](https://clawhub.ai/user/athola)
\n- [Homepage from Clawdis metadata](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown]
\n**Output Format:** [Markdown review guidance with scrutiny questions, anti-pattern checks, and burden-of-proof verdicts]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May activate during code-review, refactor-planning, or addition-scrutiny discussions based on broad trigger wording.]
\n\n## Skill Version(s):
\n1.9.14 (source: server release metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.9.13: 3 files, 3690 bytes\n\nFiles: skill-card.md (1984b), SKILL.md (4479b), _meta.json (152b)\n\nFile v1.9.13:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.9.13:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.13\",\n \"publishedAt\": 1782577163613\n}\n\nFile v1.9.13:skill-card.md\n\n## Description:
\nInverts burden of proof for code additions.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and code-review agents use this skill to challenge proposed code, file, abstraction, test, configuration, or error-handling additions before accepting them. It is intended for reviews, refactors, planning, and unbloat-style reduction work where evidence and consequences should justify new additions.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill can make an agent more conservative during reviews, refactors, and planning, which may over-challenge useful additions when broad trigger phrases apply.
\nMitigation: Use it where added-code scrutiny is desired, and narrow or remove broad trigger phrases if the review posture becomes too intrusive.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense)
\n- [Leyline source homepage](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)
\n\n\n## Skill Output:
\n**Output Type(s):** [Guidance, Analysis, Markdown]
\n**Output Format:** [Markdown guidance with scrutiny questions, anti-pattern checks, and burden-of-proof verdicts]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Non-executing guidance skill; produces review posture and verdict language rather than files, commands, or API calls.]
\n\n## Skill Version(s):
\n1.9.13 (source: server release evidence and target metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.9.12: 3 files, 3790 bytes\n\nFiles: skill-card.md (2269b), SKILL.md (4479b), _meta.json (152b)\n\nFile v1.9.12:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.9.12:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.12\",\n \"publishedAt\": 1781838819949\n}\n\nFile v1.9.12:skill-card.md\n\n## Description:
\nInverts burden of proof for code additions.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and code-review agents use this skill to challenge proposed code, file, abstraction, test, configuration, and error-handling additions before accepting them. It helps reviewers require concrete evidence and a burden-of-proof verdict for additions that may reflect additive bias.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Code diffs and review context may be processed by the selected reviewer CLI or provider.
\nMitigation: Use the skill only for repositories where that processing is acceptable, and disable web search where the chosen tooling supports it.
\nRisk: Broad closeout triggers may apply the review posture more often than intended.
\nMitigation: Invoke the skill explicitly for sensitive repositories or workflows that need tighter control.
\nRisk: The skill produces review guidance and verdicts that can be incomplete or overly conservative.
\nMitigation: Treat verdicts as reviewer input and require human judgment before removing or rejecting proposed work.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/nm-leyline-additive-bias-defense)
\n- [Leyline plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown, text]
\n**Output Format:** [Markdown or text review guidance with scrutiny questions and burden-of-proof verdicts]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Produces qualitative review prompts and verdict labels such as justified, needs_evidence, or unjustified.]
\n\n## Skill Version(s):
\n1.9.12 (source: ClawHub release evidence)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.0.0: 3 files, 3664 bytes\n\nFiles: skill-card.md (1959b), SKILL.md (4479b), _meta.json (151b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the addition | Proceed |\n| `needs_evidence` | Plausible but unproven | Provide evidence or remove |\n| `unjustified` | No evidence, likely bias | Remove or justify |\n\n## Integration Contract\n\nReview-oriented skills MUST consult this contract by:\n\n1. Applying the 5 scrutiny questions to each addition\n2. Scanning for the 6 anti-patterns\n3. Producing a burden-of-proof verdict\n4. Including the verdict in their output\n\n### Consuming Skills\n\n| Skill | Integration Point |\n|-------|-------------------|\n| `attune:war-room` | Prosecution Counsel role uses scrutiny questions |\n| `sanctum:pr-review` | Every added file/function challenged |\n| `pensive:code-refinement` | Refactors pass \"3rd use\" test |\n| `conserve:unbloat` | Findings feed removal candidates |\n| `attune:mission-orchestrator` | Plan sections scanned before user review |\n| `imbue:justify` | Scrutiny questions extend audit protocol |\n\n## Related Skills\n\n- `imbue:karpathy-principles` - \"Simplicity First\" and \"Surgical Changes\" principles invoke this contract from a higher-level four-principle synthesis\n- See `docs/quality-gates.md#skill-level-quality-gate-composition` for the full gate-skill federation graph\n\n## The Subtraction Principle\n\n> Rely less on AI and initial lines of thinking.\n> Challenge yourself to think of a more elegant\n> implementation or a simpler solution.\n\nBefore accepting any addition, ask: \"Could I achieve\nthis by removing code instead of adding it?\" If yes,\nprefer the subtractive approach.\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1781791738690\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nInverts burden of proof for code additions.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[athola](https://clawhub.ai/user/athola)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and engineering review agents use this skill to challenge proposed code additions, refactors, abstractions, tests, and configuration changes before accepting new complexity.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The broad triggers may apply this checklist during general engineering conversations.
\nMitigation: Disable the skill or invoke it explicitly when the checklist should be limited to specific reviews or refactors.
\nRisk: Review guidance may discourage useful additions if treated as a hard policy instead of an advisory checklist.
\nMitigation: Use the burden-of-proof verdict alongside task requirements, reproduction evidence, and human review.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/athola/nm-leyline-additive-bias-defense)
\n- [Skill homepage from clawdis metadata](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)
\n\n\n## Skill Output:
\n**Output Type(s):** [Guidance, Analysis, Markdown]
\n**Output Format:** [Markdown guidance with checklist-style review verdicts]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Produces advisory scrutiny questions, anti-pattern checks, and burden-of-proof verdicts; it does not execute code or access data.]
\n\n## Skill Version(s):
\n1.0.0 (source: server release metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
","readmeExcerpt":"Skill: additive-bias-defense Owner: athola Summary: Inverts burden of proof for code additions Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:13:54.522Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:35:07.810Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:51:50.805Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:00:47.850Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16:19:23.613Z | user Release v1.9.1","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: additive-bias-defense\ndescription: Inverts burden of proof for code additions\nversion: 1.9.8\ntriggers:\n - additive-bias\n - burden-of-proof\n - scrutiny\n - cross-cutting\n - defense\n - reviewing PRs\n - planning refactors\n - or running unbloat to challenge every addition's necessity\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/leyline\", \"emoji\": \"\\ud83e\\udd9e\"}}\nsource: claude-night-market\nsource_plugin: leyline\n---\n\n> **Night Market Skill** — ported from [claude-night-market/leyline](https://github.com/athola/claude-night-market/tree/master/plugins/leyline). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n> The default answer to \"should we add this?\" is no.\n> The burden of proof is on the addition.\n\n# Additive Bias Defense\n\n> **Note (#444):** Frontmatter declares ``provides.guidance``, not\n> ``provides.contract``. The scrutiny questions are consumed by\n> partner skills (``pensive:code-refinement``, ``conserve:unbloat``,\n> ``imbue:scope-guard``) that voluntarily embed them; no validator or\n> hook in leyline enforces them directly. If a future contributor\n> adds enforcement, restore the ``contract`` label and link the\n> validator path here.\n\n## The Problem\n\nLLMs are additive by nature. They reinvent wheels, add\nunnecessary complexity, hallucinate issues and modify\ntests to justify them, and deviate from priorities. This\ncontract provides a systemic defense.\n\n## The Scrutiny Questions\n\nApplied to every proposed addition -- code, files,\nabstractions, error handling, configuration:\n\n1. **Priority alignment**: Is this a deviation from the\n current priority?\n2. **Criticality**: Is it critical to implement at this\n juncture?\n3. **Simplicity**: Does a simpler or more elegant\n solution exist?\n4. **Evidence**: What evidence proves this is needed\n (not assumed)?\n5. **Consequence**: What breaks if we do not add this?\n\nIf the proposer cannot answer questions 4 and 5 with\nconcrete evidence, the addition is unjustified.\n\n## Anti-Pattern Detection\n\n| Pattern | Signal | Challenge |\n|---------|--------|-----------|\n| Wheel reinvention | New utility/helper overlapping existing code | \"Does X already do this?\" |\n| Hallucinated issues | Fix for a bug with no reproduction evidence | \"Show the failing test before the fix\" |\n| Test manipulation | Test changed to match behavior rather than spec | \"Did the spec change, or did you change the test?\" |\n| Complexity creep | Abstraction introduced for single use case | \"Is this the 3rd use, or the 1st?\" |\n| Priority deviation | Work not traceable to current task/spec | \"Which requirement does this serve?\" |\n| Gold plating | Error handling or flexibility beyond need | \"What breaks without this?\" |\n\n## Burden of Proof Verdict\n\nAfter applying scrutiny questions and anti-pattern\ndetection, produce a verdict:\n\n| Verdict | Meaning | Action |\n|---------|---------|--------|\n| `justified` | Evidence supports the a"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n \"slug\": \"nm-leyline-additive-bias-defense\",\n \"version\": \"1.9.19\",\n \"publishedAt\": 1787750034522\n}"},{"path":"skill-card.md","content":"## Description:\n\nInverts burden of proof for code additions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[athola](https://clawhub.ai/user/athola)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering agents use this skill during reviews, refactors, planning, and cleanup work to challenge proposed additions with evidence-focused scrutiny questions and anti-pattern checks.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The broad triggers and strong burden-of-proof framing may make an agent push back more often than desired in general engineering discussions.\n\nMitigation: Apply the skill primarily during reviews, refactors, planning, and cleanup work where evidence-based scrutiny of additions is desired.\n\nRisk: A justified addition may be delayed if its rationale or consequence is not documented clearly.\n\nMitigation: Ask for concise evidence explaining why the addition is needed and what breaks without it before accepting a needs_evidence or unjustified verdict.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-leyline-additive-bias-defense)\n- [OpenClaw homepage](https://github.com/athola/claude-night-market/tree/master/plugins/leyline)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Text]\n\n**Output Format:** [Markdown guidance with scrutiny questions, anti-pattern checks, and verdict labels]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [No code execution, persistence, credential access, or hidden data handling reported by security evidence.]\n\n## Skill Version(s):\n\n1.9.19 (source: ClawHub release metadata; artifact frontmatter reports 1.9.8)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Inverts burden of proof for code additions Skill: additive-bias-defense Owner: athola Summary: Inverts burden of proof for code additions Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:13:54.522Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:35:07.810Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:51:50.805Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:00:47.850Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16:19:23.613Z | user Release v1.9.1","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1139,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:10:58.017Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:10:58.017Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-14T10:43:54.923Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}