Xpersona
agentCLAWHUBUnverified

Relay Knowledge CLI

Code-map-backed repository knowledge loop Skill: Relay Knowledge CLI Owner: stevetdp Summary: Code-map-backed repository knowledge loop Tags: latest:1.1.19 Version history: v1.1.19 | 2026-10-09T09:56:04.984Z | user relay-knowledge v1.1.19 v1.1.18 | 2026-09-18T06:41:21.896Z | user relay-knowledge v1.1.18 v1.1.17 | 2026-09-07T09:01:17.461Z | user relay-knowledge v1.1.17 v1.1.16 | 2026-08-30T01:27:56.532Z | user relay-knowledge v1.1.16 v1.1.14 | 2026-08-27T03:4

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

2.1k

Updated

Oct 9, 2026

Version

1.1.19

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.1K downloads reported by the source. Last updated 10/9/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 9, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 9, 2026
Adoption signal
2.1K downloadsadoption · observed Oct 9, 2026
Latest release
1.1.19release · observed Oct 9, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s175261s0xvkyprt3f0vdgxm8h84hkx6:relay-knowledge-cli
  1. 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.
  2. 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: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-stevetdp-relay-knowledge-cli/snapshot"

Documentation

CLAWHUB

145,627 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: relay-knowledge-cli
description: "Use relay-knowledge local CLI for repository CodeSpec/Knowledge map governance and GraphRAG: initialize, validate, route, and update codespec/codespec-map.yaml and knowledge/knowledge-map.yaml; read snapshot-bound repo business/software/view/context models for specs and coding; run durable update/status/impact loops after commits. Use for 目录化知识管理, 知识地图初始化, 业务术语与技术映射, git commit知识库增量更新, 用户代码查询kind/查询类型, 图关系, 调用关系, 导入依赖, SDK/API, definitions, references, usage, impact. Prefer graph CLI before grep/rg unless unavailable, unindexable, inexpressible, or raw regex is required. Do not use for MCP/ACP setup or protocol access."
metadata:
  version: 1.1.19
  openclaw:
    skillKey: relay-knowledge-cli
    homepage: https://github.com/coolplayagent/relay-knowledge
---

# Relay Knowledge CLI

## Workflow

Use the compiled `relay-knowledge` binary as the control surface. Resolve the
executable before the first operation. Prefer JSON output for automation and
read command metadata before issuing unfamiliar commands.

Treat cold and incremental repository indexing as status-driven workflows, not
single long foreground waits. `repo index` and `repo update` submit durable
single-writer tasks; a local CLI invocation may also run one bounded worker
attempt before rendering its response. If the command runner times out before
JSON is captured, recover through
`repo status <alias> --format json` and inspect `active_task`, checkpoint counters, and
freshness before retrying. If a managed platform service is already draining
the code-index queue, poll status and do not start a competing worker. If no
managed service is draining work and status shows a running task after the
command runner killed a foreground attempt, inspect `lease_expires_at_ms` and
checkpoint timestamps and wait for lease recovery before retrying. When
`repo status` or the index/update response shows a queued or retrying code-index
task, let the remote managed service drain it; only a local/service-host client
may run bounded single-shot `repo index-worker --task-id <task-id> --format
json` attempts before re-checking status. Do not replace leases with loops.

Prefer the bundled `assets` binary for the current operating system, CPU, and
active command runner whenever it exists and `version --format json` succeeds.
GitHub Release skill archives include Linux x64 and Windows x64 binaries at
`assets/linux-x86_64/relay-knowledge` and
`assets/windows-x86_64/relay-knowledge.exe`. Registry distributions such as
ClawHub omit these binaries to satisfy per-file limits. Use the published `PATH`
install when the bundled asset is missing, not executable, fails its version
check, has no matching OS or CPU architecture, has no matching shell boundary,
the Linux host is older than the glibc 2.28 baseline, or the user explicitly
asks for the system-installed binary. Version comparisons are diagnostic only;
do not choose a newer `PATH` binary over a working bundled asset by

README.md

# Relay Knowledge CLI Skill

This ClawHub-compatible skill teaches LLM agents to operate `relay-knowledge`
through the local CLI. It is for local knowledge graph ingestion, hybrid
GraphRAG queries, code repository indexing, code graph search, multi-repository
queries, authored business-term and technical-mapping queries, software graph
relationship queries, feature flag graph queries,
OKF Markdown neighborhoods, commit-driven impact/context loops, setup
diagnostics, installation checks, and upgrade checks. For large repositories,
it tells agents to treat cold and incremental indexing as durable single-writer
tasks so command-runner timeouts do not interrupt or obscure progress.

For software experience gaps, the skill also documents the native
[feedback workflow](references/feedback-workflows.md), a strict version 1
[input schema](references/feedback.schema.json) and a public
[example report](references/feedback-report.example.json). Publication requires
explicit persisted opt-in; runner validation is separately authorized. These
input DTOs reject unknown fields, unlike forward-compatible Knowledge Map readers.

Repository bootstrap initializes or upgrades the
`codespec/codespec-map.yaml`, `knowledge/knowledge-map.yaml`, and the code map as one recoverable
workflow. The YAML contains stable `software-model` and `business-knowledge`
routes; the latter points to the version-controlled authored
`knowledge/glossary/business-glossary.yaml`. Snapshot-bound business, architecture,
build, deployment, dependency, and design facts remain in the indexed `repo
business`/`repo software`/`repo view` read models. Before a spec or coding task,
agents pin one ref and combine those models with business/domain views and code
context. After a commit, they refresh the durable code task, impact/context
evidence, and final map validation together.

The bundle includes Draft 2020-12 JSON Schemas for all four persisted Knowledge
Map v2 artifact classes and for the authored Business Glossary v1 document.
They support machine-readable field discovery and structural checks without
replacing the CLI's runtime and semantic validation. Unknown fields remain
accepted to match current Serde readers. The Knowledge Map schema does not make
generated shards, archives, or index nodes agent-editable; the separate glossary
schema describes a version-controlled source that is intentionally edited under
normal review.

For code-structure questions such as function definitions, symbol locations,
references, callers, callees, call graphs, and call chains, agents should use
this skill before `grep`, `ripgrep`, `rg`, or plain text search. Fall back to
text search only when the CLI cannot satisfy the request, the target repository
cannot be indexed, or the user explicitly needs raw text or regular-expression
matching.

For `repo query --kind` prompts, the supported code query kinds are `hybrid`,
`symbol`, `definition`, `references`, `callers`, `callees`, `imports`, and
`sbom`. Agents should

_meta.json

{
  "ownerId": "kn7ftpbqzwq14ga3f5ms64h1yn84hc25",
  "slug": "relay-knowledge-cli",
  "version": "1.1.19",
  "publishedAt": 1791539764984
}

references/authored-evidence-bundle.schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "authored-evidence-bundle.schema.json",
  "title": "authored-evidence-bundle",
  "$comment": "Runtime also enforces UTF-8 byte budgets, source scopes, confined paths, stable identities and exact span/hash bindings.",
  "type": "object",
  "properties": {
    "schema_version": {
      "const": 1
    },
    "id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128
    },
    "source_scope": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4096,
      "pattern": "^\\S(?:[\\s\\S]*\\S)?$"
    },
    "graph": {
      "type": "object",
      "properties": {
        "nodes": {
          "type": "array",
          "minItems": 1,
          "maxItems": 512,
          "items": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string",
                "minLength": 1,
                "maxLength": 256
              },
              "kind": {
                "type": "string",
                "minLength": 1,
                "maxLength": 256
              },
              "label": {
                "type": "string",
                "minLength": 1,
                "maxLength": 1024
              }
            },
            "required": [
              "id",
              "kind",
              "label"
            ],
            "additionalProperties": true
          }
        },
        "edges": {
          "type": "array",
          "maxItems": 2048,
          "items": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string",
                "minLength": 1,
                "maxLength": 256
              },
              "source": {
                "type": "string",
                "minLength": 1,
                "maxLength": 256
              },
              "target": {
                "type": "string",
                "minLength": 1,
                "maxLength": 256
              },
              "relation": {
                "type": "string",
                "minLength": 1,
                "maxLength": 256
              },
              "evidence": {
                "type": "array",
                "maxItems": 32,
                "items": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 4096
                }
              }
            },
            "required": [
              "source",
              "target",
              "relation"
            ],
            "additionalProperties": true
          }
        }
      },
      "required": [
        "nodes",
        "edges"
      ],
      "additionalProperties": true
    },
    "evidence": {
      "type": "array",
      "maxItems": 512,
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 4096
          },
          "source_sc

references/business-glossary.schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Relay Knowledge Business Glossary v1",
  "description": "Machine-readable structural schema for the authored knowledge/glossary/business-glossary.yaml contract; migration readers also accept the legacy .knowledge/business-glossary.yaml path. Objects intentionally allow unknown fields to remain compatible with the Serde readers. JSON Schema maxLength counts Unicode characters, while relay-knowledge enforces UTF-8 byte limits, the 4194304-byte document limit, domain and term identity, domain references, and case-insensitive alias uniqueness; relay-knowledge map validate is authoritative for those semantic checks. Unlike generated Knowledge Map artifacts, the version-controlled business glossary is intentionally authored and may be edited directly with normal source review.",
  "type": "object",
  "required": [
    "schema_version"
  ],
  "properties": {
    "schema_version": {
      "type": "integer",
      "const": 1
    },
    "domains": {
      "type": "array",
      "maxItems": 256,
      "uniqueItems": true,
      "default": [],
      "items": {
        "$ref": "#/$defs/domain"
      }
    },
    "terms": {
      "type": "array",
      "maxItems": 10000,
      "uniqueItems": true,
      "default": [],
      "items": {
        "$ref": "#/$defs/term"
      }
    }
  },
  "additionalProperties": true,
  "$defs": {
    "text128": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128,
      "pattern": "^(?=.*\\S)[^\\u0000]*$"
    },
    "text1024": {
      "type": "string",
      "minLength": 1,
      "maxLength": 1024,
      "pattern": "^(?=.*\\S)[^\\u0000]*$"
    },
    "text32768": {
      "type": "string",
      "minLength": 1,
      "maxLength": 32768,
      "pattern": "^(?=.*\\S)[^\\u0000]*$"
    },
    "nullableText128": {
      "type": [
        "string",
        "null"
      ],
      "minLength": 1,
      "maxLength": 128,
      "pattern": "^(?=.*\\S)[^\\u0000]*$"
    },
    "nullableText1024": {
      "type": [
        "string",
        "null"
      ],
      "minLength": 1,
      "maxLength": 1024,
      "pattern": "^(?=.*\\S)[^\\u0000]*$"
    },
    "nullableText32768": {
      "type": [
        "string",
        "null"
      ],
      "minLength": 1,
      "maxLength": 32768,
      "pattern": "^(?=.*\\S)[^\\u0000]*$"
    },
    "domain": {
      "type": "object",
      "required": [
        "id",
        "name"
      ],
      "properties": {
        "id": {
          "$ref": "#/$defs/text128"
        },
        "name": {
          "$ref": "#/$defs/text1024"
        },
        "description": {
          "$ref": "#/$defs/nullableText32768"
        }
      },
      "additionalProperties": true
    },
    "termStatus": {
      "type": "string",
      "enum": [
        "active",
        "deprecated"
      ]
    },
    "aliasKind": {
      "type": "string",
      "enum": [
        "synonym",
        "abbreviation"
      ]
    },
    "mappingRelation": {

Related agents

Same protocol, similar job.

Github ReposUpdated 5h agoRank 70

AionUi

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!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

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

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/stevetdp/skills/relay-knowledge-cli",
      "sourceUrl": "https://clawhub.ai/stevetdp/skills/relay-knowledge-cli",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T18:48:37.170Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-stevetdp-relay-knowledge-cli/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-stevetdp-relay-knowledge-cli/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T18:48:37.170Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.1K downloads",
      "href": "https://clawhub.ai/stevetdp/relay-knowledge-cli",
      "sourceUrl": "https://clawhub.ai/stevetdp/relay-knowledge-cli",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T18:48:37.170Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.1.19",
      "href": "https://clawhub.ai/stevetdp/relay-knowledge-cli",
      "sourceUrl": "https://clawhub.ai/stevetdp/relay-knowledge-cli",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-10-09T09:56:04.984Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-stevetdp-relay-knowledge-cli/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-stevetdp-relay-knowledge-cli/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.1.19",
      "description": "relay-knowledge v1.1.19",
      "href": "https://clawhub.ai/stevetdp/relay-knowledge-cli",
      "sourceUrl": "https://clawhub.ai/stevetdp/relay-knowledge-cli",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-10-09T09:56:04.984Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

Sponsored

Ads related to Relay Knowledge CLI and adjacent AI workflows.