Borrowing it
Nothing to install: this file belongs to terrene-foundation/metis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/terrene-foundation/metis/main/.claude/commands/cli-audit.mdgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/commands/terrene-foundation/metis/cli-audit)<a href="https://agentmods.dev/commands/terrene-foundation/metis/cli-audit"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/cli-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/commands/terrene-foundation/metis/cli-audit"><img src="https://agentmods.dev/badge/commands/terrene-foundation/metis/cli-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.01570 |
| Opus 5.5 | $0.00012 | $0.00628 |
| Sonnet 5.5 | $0.00006 | $0.00314 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
cli-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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-CLI Audit
Dispatch entry point for cli-orchestrator.audits per spec v6 §6.2. Reviews the full multi-CLI emission pipeline (source rules → slot overlays → abridgement → per-CLI target files) for parity, drift, and cap compliance across CC, Codex, and Gemini.
Your Role
Specify scope: all (default), emission, parity, drift, or validators.
Dispatch Contract (v6 §6.2)
You MUST dispatch cc-architect, codex-architect, and gemini-architect via the Task tool in the SAME TURN with run_in_background: true (parallel launch per rules/agents.md § Parallel Execution). Sequential dispatch is BLOCKED — it bypasses the parallel-execution multiplier and re-runs the same audit three times in series.
# DO — single turn, three parallel architects
Agent(subagent_type="cc-architect", run_in_background=true, prompt="...CC audit brief with emission report...")
Agent(subagent_type="codex-architect", run_in_background=true, prompt="...Codex audit brief with AGENTS.md...")
Agent(subagent_type="gemini-architect", run_in_background=true, prompt="...Gemini audit brief with GEMINI.md...")
# DO NOT — sequential
Agent(subagent_type="cc-architect", ...) # wait for return
Agent(subagent_type="codex-architect", ...) # then this
Phase 1: Produce the emission (dry-run)
Run the E4 emitter in dry-run mode to produce per-CLI baseline emissions the architects will audit:
node .claude/bin/emit.mjs --all --out /tmp/cli-audit-$(date +%s) -v
This writes:
/tmp/cli-audit-<ts>/codex/AGENTS.md+emit-report-codex.json/tmp/cli-audit-<ts>/gemini/GEMINI.md+emit-report-gemini.json/tmp/cli-audit-<ts>/codex-mcp-guard/policies.json(V13 POLICIES table)/tmp/cli-audit-<ts>/emit-telemetry.json— consolidated headroom summary (per-CLI bytes, tier, headroom_bytes, headroom_pct) keyed offwarn_cap_bytes+block_cap_bytesloaded fromsync-manifest.yaml. Surfaces the trend metric for Risk-0004 (baseline-cap headroom ~4%).
Exit code ≠ 0 means V12 slot-round-trip failed, V13 MCP bijection failed, or the emission exceeded block_cap_bytes. A non-zero exit is a HARD BLOCK on this audit — fix before dispatching architects.
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.
- 1mo ago First seen · 97 lines · 30 tokens per session scan A ff1456b417d4
cli-audit is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,570 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).