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 gtrabanco/agentic-workflow --skill audit-prgit clone --depth 1 https://github.com/gtrabanco/agentic-workflowWrote 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/gtrabanco/agentic-workflow/audit-pr)<a href="https://agentmods.dev/skills/gtrabanco/agentic-workflow/audit-pr"><img src="https://agentmods.dev/badge/skills/gtrabanco/agentic-workflow/audit-pr/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/gtrabanco/agentic-workflow/audit-pr"><img src="https://agentmods.dev/badge/skills/gtrabanco/agentic-workflow/audit-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.02916 |
| Opus 5.5 | $0.00028 | $0.01166 |
| Sonnet 5.5 | $0.00014 | $0.00583 |
| Haiku 4.5 | $0.00007 | $0.00292 |
Grade A, and why
audit-pr 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 11d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit PR
The manager's "can this ship?" gate. A read-first audit over the entire PR —
its SPEC, all phases, docs, CI status, and review receipt — that returns a single
verdict: merge-ready or a ranked list of blockers. Never edits,
refactors, or merges. The human merges, or an active
advance --fullauto invocation consumes the SHA-bound verdict and performs
its separate fail-closed merge step.
audit-pr does not re-review the diff. It consumes the current SHA-bound
review-change receipt (the REVIEW-PASS comment marker) as the review
evidence, blocks on a missing or stale receipt routed to /review-change, and
independently evaluates only the delivery gates below.
Turn contract — verify before ending the turn
✓ The review receipt was consumed from one PR snapshot: `headRefOid` + newest
matching `review-change:pass` marker fetched together; absent or any SHA
mismatch → blocker routed to `/review-change`, current → its scope/axes/
acceptance coverage/manual checks acknowledged without re-review
✓ Terminal hygiene was read from state, not assumed: tree clean, branch pushed,
PR not a draft (`bun scripts/audit-pr-gate.mjs hygiene --pr <N> --apply`)
✓ Upstream lineage was re-verified (current plan receipt + parent spec receipt,
digests recomputed), every obligation row is `verified`/`n/a`, and no planning
finding is open — stale or missing lineage is a blocker, never a formality
✓ The verdict block was printed in the fixed format: `VERDICT: MERGE-READY | BLOCKED` with ranked, evidenced blockers
✓ The PR's FULL URL is printed in the verdict header (the user may be juggling
several projects and agents without a CI monitor — the link in the chat is
the contract, never "PR #N" alone)
✓ MERGE-READY verdict? Then the comment was POSTED by
`bun scripts/audit-pr-gate.mjs comment` (re-reads, exits non-zero unless the newest marker
names the head) — a comment, never a commit-message tag. BLOCKED → no comment
✓ Nothing was edited, refactored, or merged; merge authorization is outside
this skill and cannot be inherited from docs or an earlier session
✓ No review pass was composed or reconstructed: a missing/stale receipt is a
blocker, never a prompt to re-run review axes from this skill
✓ Closure integrity was evaluated and its result stated explicitly: pass /
blocker / n-a (fix-governed PRs are always n-a; never skipped
silently)
✓ Scope integrity (descope) was evaluated and its result stated explicitly:
pass / blocker / n-a (no unit-referencing issues born on the branch → n-a;
never skipped silently)
✓ Architectural-invariant preservation was evaluated and its result stated
explicitly: pass / blocker / n-a (no project document → n-a; never skipped)
✓ The closing `→ Next:` block is printed as the ABSOLUTE last output
What ships with it
6 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.
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.
- 11d ago Changed 4268f38bb5e9
- 12d ago Changed · +11 lines ce43692f1354
- 24d ago Changed a4ae210e057c
- 27d ago Changed be3c852ab576
- 1mo ago Changed · +2 lines cb2eb5b05b44
- 1mo ago Changed 7f5b6d3781fb
- 1mo ago Changed · +3 lines f31bc7549746
- 1mo ago First seen · 202 lines · 71 tokens per session scan A 94a4c33b6711
audit-pr is a skill published in the GitHub repository gtrabanco/agentic-workflow (22 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 2,916 once invoked, about $0.0003 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
create-pull-request
Create and manage pull requests using GitHub CLI. Covers branch preparation, writing PR titles and descriptions, creating PRs, handling review feedback, and merge/cleanup workflows. Use when proposing changes from a feature or fix branch for review, merging completed work into the main branch, requesting code review…
review-gate
HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met.
pr-description-writer
Redacta una descripción de pull request clara y estructurada a partir de un diff de git, resumen de rama o lista de commits. Úsalo cuando te pidan escribir una descripción de PR, redactar una solicitud de cambios o documentar cambios de código. Produce una descripción con resumen, motivación, cambios realizados, pasos…
resolve-pr-comments
Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using the rationale recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, posts via GraphQL, and resolves threads whose entry carries a resolution reason. Use when the user asks to "reply to PR threads", "post PR thread…
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.