Borrowing it
Nothing to install: this file belongs to CorridorTech/PoseCap. 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/CorridorTech/PoseCap/main/.agents/skills/ad-audit/SKILL.mdgit clone --depth 1 https://github.com/CorridorTech/PoseCapWrote 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/corridortech/posecap/ad-audit)<a href="https://agentmods.dev/skills/corridortech/posecap/ad-audit"><img src="https://agentmods.dev/badge/skills/corridortech/posecap/ad-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/corridortech/posecap/ad-audit"><img src="https://agentmods.dev/badge/skills/corridortech/posecap/ad-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 22 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.
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 | $0.00241 | $0.02463 |
| Opus 5.5 | $0.00096 | $0.00985 |
| Sonnet 5.5 | $0.00048 | $0.00493 |
| Haiku 4.5 | $0.00024 | $0.00246 |
Grade A, and why
ad-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 2mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mechanical shape:
THIS SESSION:
1. Target + tree (what is under audit, and on which tree/SHA?).
2. Resolve the rule-set: repo binding docs (always) + curated store at
$AGENTIC_RULES_DIR or ~/.agentic/rules/ (optional) + project rules at
.agentic/rules/ (optional). The rule-set defines the groups and any
CRITICAL tag — never hardcode them.
3. Enumerate every group. For each: review it, or record explicit N/A + reason.
4. Write the assembled context to .agentic/reviews/<ISO>-audit-<scope>.md (audit trail).
5. Review each dispatched group in this session, as a checklist. Output one
section per group; give EVERY rule an explicit verdict.
6. Coverage matrix + verdict (never "approve") + rule-gap handoff to /ad-level-up.
The per-group checklist is the rigor: every rule gets a verdict, so a silent gap cannot masquerade as "all clear". A single-session reviewer with everything loaded can still rationalize — so for CRITICAL groups the skill recommends the user-initiated subagent escalation (Step 6), which restores true isolation and adds the cross-model pass.
<background_information>
The maximum quality gate. Where ad-review runs a light two-axis pass over a diff, ad-audit walks the project's whole rule-set as a checklist against a target bound for the team — proving every rule was checked, grounding every finding, and hardening critical rules with a second model. On Claude Code this is parallel Task subagents (one per group) plus a cross-model second pass; on Codex it is a single-session per-group checklist with a user-initiated subagent escalation for isolation and the cross-model pass. The rule-set location convention is ADR-0035; the mechanism is ADR-0036. It writes nothing to the rule-set — it audits, then hands genuine gaps to /ad-level-up.
</background_information>
Running ad-audit (Codex single-pass, per-group checklist). I will resolve the rule-set (repo binding docs + optional ~/.agentic/rules/ + optional .agentic/rules/ project layer), enumerate every group, write an audit trail to .agentic/reviews/, then give every rule an explicit verdict grouped by rule-group, with a coverage matrix. I never emit "approve".
NOTE on fidelity: a single session with everything loaded can rationalize across groups. For any group the rule-set marks CRITICAL, I will recommend the user-initiated subagent escalation at Step 6 — true isolation plus a cross-model pass against the persisted trail. The escalation TOML schema is at the bottom of this skill.
What ships with it
1 file 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.
- 2mo ago First seen · 94 lines · 241 tokens per session scan A 6e0527d0fd0a
ad-audit is a skill published in the GitHub repository CorridorTech/PoseCap (265 stars, last pushed 3d ago), licensed Apache-2.0. It adds 241 tokens to every session and 2,463 once invoked, about $0.0010 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…