Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AlexZio00/sovereign-skills --skill collab-auditgit clone --depth 1 https://github.com/AlexZio00/sovereign-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alexzio00/sovereign-skills/collab-audit)<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/collab-audit"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/collab-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/collab-audit"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/collab-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 152 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 194 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 254 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 367 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 462 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 217 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00179 | $0.07914 |
| Opus 5.5 | $0.00072 | $0.03166 |
| Sonnet 5.5 | $0.00036 | $0.01583 |
| Haiku 4.5 | $0.00018 | $0.00791 |
Grade A, and why
collab-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/collab-audit — AI Collaboration Audit
Purpose
Analyzes conversation history, artifacts, and work patterns to generate behavioral and psychological insights. Based on direct behavioral observation during actual work rather than self-report surveys. More accurate than survey-based methods.
Dominant Variable
Whether the analysis infers reasons behind observed patterns, not just lists facts (facts alone ≠ success)
Trigger
/collab-audit- Natural-language phrases (English and Korean) are listed in the frontmatter
triggersanddescription.
Discard If
- Fewer than 2 observed sessions AND fewer than 100 messages — insufficient sample to extract patterns
- Simple code review request → this skill does not review code; do a normal code review instead
- Only quantitative session metrics needed → run the Step 0 scripts and report their JSON; no 14-section report is needed
Key Assumptions
- 2+ observed sessions OR 100+ messages (meeting either one is enough) — if both are broken: Discard If triggers.
- Access to memory/session-handoff-LATEST.md — if broken (file missing): handoff pattern analysis unavailable, skip that dimension.
- Invocation ledger
~/.claude/.harness/invocations/*.jsonl(written by session-checkpoint) — optional. If it does not exist, Section 7 says "no log" for invocation counts. File formats: https://github.com/AlexZio00/sovereign-skills/blob/master/docs/FILE-CONVENTIONS.md
Mode Detection (execute first)
- Input contains
/collab-audit compareor "compare" → Compare mode (separate section below) - Otherwise → Audit mode (14-section analysis)
Input Validation (Step 0 — execute first)
Minimum conditions — one of:
- 2+ sessions
- 100+ messages
- Single-session high-density exception → refer to Invariant 4 criteria. If exception met, mark
⚠ Single-session analysis — pattern confidence limitedthen proceed.
Deterministic gate (preferred): if session-meta JSON files are available (one per session, with fields such as message_count, artifact_count, originator, first_message, cwd), run python3 "${CLAUDE_SKILL_DIR}/scripts/session_hygiene_scan.py" --meta-dir <DIR> and read meets_minimum / single_session_exception straight from its JSON output — do not re-derive these booleans by eyeballing the transcripts. Fall back to manual counting only when no such metadata directory exists (e.g. a single live conversation with no file access).
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 595 B
- agents/openai.yaml 171 B
- scripts/extract_session_meta.py 6.5 KB runs code
- scripts/harness_log_counts.py 4.4 KB runs code
- scripts/session_hygiene_scan.py 7.9 KB runs code
- scripts/test_extract_session_meta.py 4.1 KB runs code
- scripts/test_harness_log_counts.py 3.0 KB runs code
- scripts/test_session_hygiene_scan.py 9.6 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed · +7 lines 995c5aeae6f8
- 18d ago Changed · +8 lines c28a48f84cd2
- 1mo ago Changed · -1 lines ea34ec3b8a1d
- 1mo ago Changed · +12 lines 69997cc78a74
- 1mo ago First seen · 511 lines · 179 tokens per session scan A 1b48bffe2d23
collab-audit is a skill published in the GitHub repository AlexZio00/sovereign-skills (149 stars, last pushed 6d ago), licensed MIT. It adds 179 tokens to every session and 7,914 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nobrainer-review
Use when the owner says nb-review, deep-audit, deep-code-review, or deep-autoreview; explicitly requests an evidence-gated CLOSEOUT, adversarial BUGHUNT or RELEASEGATE; or needs final findings filtered to verified actionable defects. Use nobrainer-build for ordinary implementation and correction work.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
ijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
oak-adversarial-review
Use for every final review of a diff - an independent pass that assumes the change is wrong, accounts for every changed file, attacks it along fixed dimensions, fact-checks its own findings and ends in an explicit verdict. Use also when the user asks for a red-team or devil's-advocate review.
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.