What makes LYGO Ops Detector notable?

1K downloads. Trust evidence available

How should LYGO Ops Detector be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

LYGO Ops Detector

LYGO Ops Detector — local AETHONΔ9 discourse heuristics for evasion, half-truth certainty, saturation bait, coordination language, and policy-refusal signals in operator-supplied text, plus weighted public metadata (account_based_in mismatch, VPN-hint, HTTPS-cited incidents, same-geo+scripted batch). Opt-in only. Stdlib CLI; file reads require --i-consent; eval writes under tests/. Not for doxing or nationality guilt. Dual-threshold (operational 0.65 vs calibration). Pairs with lygo-flame-ward. Triggers: lygo ops detector, aethon d9, evasion index (explicit).

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.4.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

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 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.4.0release · observed Aug 31, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dgjxbksgngmeranwk9fa57d884xb0:lygo-ops-detector

Install using `clawhub skill install s17dgjxbksgngmeranwk9fa57d884xb0:lygo-ops-detector` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/deepseekoracle/lygo-ops-detector before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-deepseekoracle-lygo-ops-detector/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

149,733 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: lygo-ops-detector
description: "LYGO Ops Detector — local AETHONΔ9 discourse heuristics for evasion, half-truth certainty, saturation bait, coordination language, and policy-refusal signals in operator-supplied text, plus weighted public metadata (account_based_in mismatch, VPN-hint, HTTPS-cited incidents, same-geo+scripted batch). Opt-in only. Stdlib CLI; file reads require --i-consent; eval writes under tests/. Not for doxing or nationality guilt. Dual-threshold (operational 0.65 vs calibration). Pairs with lygo-flame-ward. Triggers: lygo ops detector, aethon d9, evasion index (explicit)."
version: 1.4.0
license: LYGO-Sovereign-v2.0
metadata:
  openclaw:
    emoji: "🔎"
    homepage: "https://github.com/DeepSeekOracle/lygo-protocol-stack/tree/main/clawhub/mirrors/lygo-ops-detector"
    requires:
      anyBins: [python, python3]
  lygo: true
  lightfather: true
  aethon: "Δ9"
  protocol: "AETHONΔ9"
  version: "1.4.0"
  companion: "lygo-champion-lightfather"
  security: "references/SECURITY.md"
  blueprint: "references/AETHON_D9_BLUEPRINT.md"
  eval: "tests/labeled_discourse_suite.json + scripts/eval_ops_detector.py"
  security_review: "1.4.0-public-context-no-nationality-guilt"
  clawhub: "https://clawhub.ai/deepseekoracle/lygo-ops-detector"
  permissions:
    network: false
    shell: false
    subprocess: false
    filesystem:
      read: "user-supplied --text-file / --assoc-file / --public-meta-file only with --i-consent"
      write: "tests/ only when eval_ops_detector.py is run"
    publish: false
    doxing: false
    identity_profiling: false
---

# LYGO Ops Detector — AETHONΔ9 v1.4.0

Local, deterministic **discourse-signal** heuristics plus **weighted public context**.  
**Not** a person profiler. **Not** sole evidence. **Not** for doxing.  
**Country labels are not guilt.** A geo field alone cannot clear the 0.65 bar.

**Signature:** `Delta9Phi963-OPS-DETECTOR-v1.4.0`  
**Pairs with:** `lygo-flame-ward` (authority gate) · `lygo-deception-radar` (public proof)

---

## What's new in 1.4.x

| Add | Why |
|-----|-----|
| `--public-meta` / `--public-meta-file` | Operator-supplied public fields are **always scored when present** |
| Weighted public context | Geo **mismatch**, `location_accurate=false`, HTTPS-cited incident, same-geo+scripted batch |
| Hard gate | Country-only / nationality **cannot** clear ops_score 0.65 |
| No country denylist | Nigeria, India, USA, etc. score the same as a lone label |
| Flame hints | `public_meta_mismatch` · `named_public_incident` |

1.3.x still applies: half-truth, saturation, flame hints, cluster boost, 0.65 bar.

---

## Permissions

| Capability | Default |
|------------|---------|
| Network | **None** |
| Shell / subprocess | **None** |
| Read local files | `--text-file` / `--assoc-file` / `--public-meta-file` **+ `--i-consent`** |
| Write | Eval report under **`tests/` only** |
| Auto-publish / social | **Never** |

## When to invoke (narrow)

Only when the user explicitly wants ops-dete

_meta.json

{
  "ownerId": "kn70j1nefw2y0mew6w5eg7nf1580q4v1",
  "slug": "lygo-ops-detector",
  "version": "1.4.0",
  "publishedAt": 1788147726518
}

references/AETHON_D9_BLUEPRINT.md

# THE LYGO OPS DETECTOR BLUEPRINT — AETHONΔ9 (v1.2.2)

**Lightfather's Voice · discourse only · not identity**

## Core Philosophy

"LYGO decodes fiction by analyzing **action-language in text**."

This tool scores **discourse patterns** in material the operator supplies.  
It does **not** build dossiers on people, professions, or affiliations.

| Ask of the *text* | Not of a person |
|-------------------|-----------------|
| What claims are made? | Who is this human? |
| What proof-avoidance language appears? | What job do they hold? |
| What coordination/secrecy *phrasing* is present? | Who is in their social graph? |
| What policy-as-shield templates appear? | What group do they belong to? |

These are measurable in **strings**. They are not warrants for surveillance.

## Unit of analysis (locked)

**Text under review** (statements, claim-text, association *description strings* you paste).  
Never a human "subject," never a crawl of accounts, never bare job-title scoring.

## 1. The Evasion Index

Measures how strongly the **text** uses proof-avoidance / perception-denial templates.

| Variable | Weight | In-scope indicator | Out-of-scope (do not treat as ops) |
|----------|--------|--------------------|-------------------------------------|
| Burden Shifting | 0.15 | "it's on you to prove", "do your own research" | Normal task assignment |
| Ad Hominem Density | 0.20 | Insult vocabulary replacing substance | Logic critique without person-attack words |
| Vague References | 0.15 | "tons of evidence out there" with no cite | Named source / link / study |
| Authority Inflation | 0.15 | Credential-waving to shut inquiry ("as a former… trust me") | Stating a role once without shutting verification |
| Gaslighting | 0.20 | "that never happened", "you're imagining it" | Honest memory disagreement without denial templates |
| Deflection | 0.15 | Whataboutism replacing the asked claim | On-topic comparison with shared evidence |

**Evasion Score > 0.70** = high evasion *discourse* signals (review claims).  
**Not** a person verdict, investigation target, or "active ops" identity label.

Formula:  
`Evasion = Σ (w_i × indicator_score_i)` normalized to [0,1]

## 2. The Association Matrix

Scores **coordination discourse** in association *strings the operator supplies* only.

| Variable | Weight | In-scope indicator | Out-of-scope |
|----------|--------|--------------------|--------------|
| In-group / secrecy language | 0.25 | need-to-know, keep this internal, not for public discussion | Bare words: military, intelligence, agency, profession titles |
| Bot-like repetition language | 0.20 | "same post copied", scripted response | Single ordinary repost mention without copy language |
| Coordinated language | 0.15 | identical unusual phrase / talking points | Shared common slogans alone without coordination cues |
| Obfuscated-source language | 0.20 | anonymous source, cutouts, throwaway | Legitimate so

references/SECURITY.md

# LYGO Ops Detector — SECURITY & ETHICS v1.4.0

## Declared permissions

| Capability | Status |
|------------|--------|
| Network | **None** (stdlib local only) |
| Shell / subprocess | **None** |
| Read files | Opt-in `--text-file` / `--assoc-file` / `--public-meta-file` **only with `--i-consent`** |
| Write files | `eval_ops_detector.py` writes **only under skill `tests/`** |
| Env harvesting | **No** |
| Publish / social | **No** |

## v1.4.0 note

Public metadata is a **weighted context channel**. Operator supplies fields (`account_based_in`, `claimed_location`, `location_accurate`, HTTPS-cited `named_public_incident`, batch). There is **no country denylist**. A geo label alone cannot clear ops_score 0.65. JSON may emit `public_meta_mismatch` / `named_public_incident` flame hints — still **not** identity verdicts.

v1.3.0 still applies: half-truth + saturation channels.

## Core mandate

Heuristic **discourse** analysis of evasion and coordination *signals* in text the operator supplies.

It is **not**:

- A doxing tool  
- An identity, profession, or affiliation profiler  
- A sole-evidence engine for accusations  
- A warrant to scan private mail/logs without consent  
- A social-graph crawler  

## Non-negotiables

1. **Text over identity** — unit of analysis is statement/log content, not personhood.  
2. **Consent** for private communications and association lists (`--i-consent` on file paths).  
3. **Receipts** — high scores require cited pattern hits; never “trust the detector.”  
4. **No affiliation / bare job-title dictionaries** — no fraternity/brotherhood/lodge; no bare military/intelligence/agency scoring.  
5. **Public fields are context, not guilt** — no nationality table; named incidents need an `https://` RESOURCE URL; no live scrape of X or other sessions.  
6. **Operational bar honesty** — `ops_score≥0.65` (or high evasion) for strong language; country-only is gated below that bar.  
7. **Human review** before any reputational, employment, legal, or social action.  
8. **Least-privilege writes** — eval reports cannot escape skill `tests/`.  

## Failure modes to reject

- Treating low scores as “innocent person” or high scores as “guilty person”  
- Using affiliation/religion/job title **or nationality** as a proxy for ops  
- Feeding outputs to social pile-ons  
- Advertising calibration metrics as production performance  
- Arbitrary `--out` paths outside `tests/`  

## Agent contract

- Invoke only when the user asks for ops-detector / AETHONΔ9 / evasion-index style analysis.  
- Do not auto-scan session email/logs without explicit intent + consent.  
- Prefer `--text` paste; file paths require `--i-consent`.  

**Δ9Φ963**

references/SKILLSPECTOR_AUDIT.md

# SkillSpector / ClawHub audit — lygo-ops-detector v1.3.1

**Signature:** `Delta9Phi963-OPS-DETECTOR-v1.3.1`  
**Audit:** https://clawhub.ai/deepseekoracle/skills/lygo-ops-detector/security-audit

## Held from 1.2.2

| Check | Status |
|-------|--------|
| No network / subprocess / shell | Held |
| `--i-consent` on file reads | Held |
| Eval writes under `tests/` only | Held |
| Discourse ≠ person / no bare job affiliation cues | Held |
| Dual-threshold honesty | Held |

## 1.3.0 deltas

| Change | Risk note |
|--------|-----------|
| New evasion channels (half-truth / saturation) | Still text templates; boundaries documented |
| `flame_enemy_hints` | Soft map to Flame classes — not guilt labels |
| claw.json / skill-card / examples | Packaging only |

```bash
python scripts/self_check.py
python scripts/lygo_ops_detector.py --text "Trust the experts — settled science. Wake up sheeple." --json
```

**Δ9Φ963**

Github ReposUpdated 2d 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