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.
git clone --depth 1 https://github.com/SienkLogic/plan-build-runWrote 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/sienklogic/plan-build-run/audit)<a href="https://agentmods.dev/commands/sienklogic/plan-build-run/audit"><img src="https://agentmods.dev/badge/commands/sienklogic/plan-build-run/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/sienklogic/plan-build-run/audit"><img src="https://agentmods.dev/badge/commands/sienklogic/plan-build-run/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 | $0.00014 | $0.00033 |
| Opus 5.5 | $0.00006 | $0.00013 |
| Sonnet 5.5 | $0.00003 | $0.00007 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
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.
What it actually says
This command is provided by the pbr:audit skill.
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 · 6 lines · 14 tokens per session scan A daddf927b73e
audit is a command published in the GitHub repository SienkLogic/plan-build-run (19 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 33 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 2026-08-30.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
adversarial-review
Coordinated three-lens adversarial review (chaos + simplifier + adversarial-reviewer) against a PRD, build plan, validation report, code, or proposal — with a fixed must-fix rubric, a mechanical pre-gate, and drift detection on the review itself.
quality-review
Run the 3-agent quality review (simplifier + adversarial-reviewer + chaos-engineer) against a plan, file, or proposal.
adversarial
Run only the adversarial-reviewer (Opus) against a target. Challenges claims and assumptions; finds logical gaps.
tech-debt
Detectar y cuantificar deuda técnica con clasificación. Usa cuando el usuario dice "deuda técnica", "technical debt", "code smells", "refactorizar", "tech debt", "code rot", "spaghetti code", "duplicación", "complejidad ciclomática", "mantenibilidad". Incluye clasificación especial para AI slop. Genera reporte con…
simplify
Run only the simplifier (Sonnet) against a target. Finds over-engineering, premature abstraction, and unnecessary indirection.