Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bdfinst/agentic-dev-team/plugin install dev-teamWrote 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/bdfinst/agentic-dev-team/agent-audit)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/agent-audit"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/agent-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/bdfinst/agentic-dev-team/agent-audit"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/agent-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 | $0.00074 | $0.07375 |
| Opus 5.5 | $0.00030 | $0.02950 |
| Sonnet 5.5 | $0.00015 | $0.01475 |
| Haiku 4.5 | $0.00007 | $0.00737 |
Grade A, and why
agent-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 — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Audit
Role: orchestrator. This skill performs mechanical compliance checks — pattern matching against known-good structure.
You have been invoked with the /agent-audit skill. Audit agents and
skills for compliance with the eval system patterns documented in
.claude/docs/eval-system.md.
Monorepo-relative by design (#1637). Steps 8 and 2e's scripts/validate_agent_contract.py and scripts/check_registry_sync.py calls are intentionally bare, not a dangling-path defect. check_registry_sync.py hardcodes plugins/dev-team and checks this marketplace repo's own registry — it exists only at this repo's root, so no ${CLAUDE_PLUGIN_ROOT} path could ever resolve it. validate_agent_contract.py's repo-root copy is a thin wrapper delegating to plugins/marketplace-dev/scripts/validate_agent_contract.py (which does ship and is portable) — but there is no single variable spanning two independently-installed plugins, so the wrapper is reachable only from this monorepo checkout, where both plugin directories are siblings on disk. Both calls only make sense run from a dev-team-monorepo-shaped checkout (this repo, or a structural fork), never an installed plugin cache. See tests/repo/test_agent_implemented_by_resolves.py's INTENTIONAL_BARE_INVOCATION set, which checks the "does not ship" premise mechanically. (#1652 landed a Bash(...) grant in this skill's allowed-tools frontmatter covering all three of these script steps — including verify_tier.py below — by their exact bare/repo-relative invocation form, so they execute today; see the allowed-tools block above.)
Orchestrator constraints
- Check structure, not semantics. Verify required sections, fields, and patterns exist. Do not evaluate whether detection rules are good — that's agent-eval's job.
- Deterministic checks only. Every check should be reproducible: does the field exist? Is the format correct? Does the section match the expected pattern?
- When
--fixis used, apply minimal structural fixes. Insert missing sections/fields using templates. Do not rewrite existing content. - Be concise. Output the report table and action items. No preambles, no per-file narration, no restating what was checked.
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 · 533 lines · 74 tokens per session scan A bad78fc3e2dd
agent-audit is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 7,375 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 2026-09-03.
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"…
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…
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…