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 agentmods add commands/aksoftcode/aicrew/harness-auditgit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00017 | $0.01575 |
| Opus 5 | $0.00009 | $0.00788 |
| Sonnet 5 | $0.00003 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
harness-audit scanned grade A with 1 finding 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 yesterday.
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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json | python3 -c "import json,sys; s=json.load(sys.stdin); print(json.dumps(s.get('hooks',{}), indent=2))" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Health-check your aicrew install — verifies hooks, symlinks, MCP wiring, and Codex skill coverage.
⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE
At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.
Known tools by platform (use if available):
Platform Checkpoint behavior Claude Code Call AskUserQuestiontool if available; otherwise end response and waitCursor Call askFollowupQuestiontool if available; otherwise end response and waitAntigravity Native ask tool if available; otherwise end response and wait Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitCodex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitAutonomous script Stops execution — never invents your answer NEVER skip a checkpoint. NEVER fabricate the user's response.
/harness-audit — AI Harness Self-Audit
Audits the Claude Code / AI agent setup itself: skills, agents, hooks, commands, memory, and platform coverage. Finds gaps, stale configs, and reliability issues.
Mode from $ARGUMENTS: quick (5-10 min read-only) or full (complete + recommendations). Default: quick.
Step 1: Skills & Agents inventory
Check ~/Agents/:
ls ~/Agents/commands/
ls ~/Agents/agents/
ls ~/Agents/hooks/
For each file, verify:
- Has
description:field with trigger conditions only (not workflow summary) - Has
⚠️ INTERACTIVE CHECKPOINTStable with all 5 platforms - Leads with the generic "use your platform's native interactive ask/question tool" instruction before the platform table
- Platform table lists known native ask tools (
AskUserQuestion,askFollowupQuestion, native ask tool e.g.ask_human) as best-effort hints, not just "end response" - Agent cross-references use
~/Agents/agents/path (not~/.claude/skills/)
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.
- yesterday First seen · 172 lines · 17 tokens per session scan A e1f193f223e8
harness-audit is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,575 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
clarify
Pre-plan interview — resolves spec ambiguity (v0.1 contract), pins the architectural lurkers from .specify/knowledge/architectural-lurkers.yaml, fires trigger-driven probes from .specify/knowledge/triggers.yaml, walks compliance scope, and writes decisions to specs/defaults/registry.yaml with provenance tagging.
cleanup
Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.
registry
Discover, create, or update the Project Defaults Registry. Scans project manifests (package.json, pyproject.toml, Cargo.toml, go.mod, etc.), batches findings for HITL confirmation, then writes specs/defaults/registry.yaml with a full audit trail in changelog.md.
specify
Create or update the feature specification from a natural language feature description.