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 antropos17/Aegis --skill audit-checkgit clone --depth 1 https://github.com/antropos17/AegisWrote 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/antropos17/aegis/audit-check)<a href="https://agentmods.dev/skills/antropos17/aegis/audit-check"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/audit-check/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/antropos17/aegis/audit-check"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/audit-check.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 | $0.00523 |
| Opus 5.5 | $0.00012 | $0.00209 |
| Sonnet 5.5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
audit-check 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 today.
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
Audit AEGIS
Record the checkout, commit and working-tree changes first. An audit reports findings; fixes follow the user's requested scope and preserve concurrent work.
For a full pre-push or pre-release audit, read AGENTS.md, package.json and .github/workflows/ci.yml, then run the verification commands defined by the current workflow. Include its type checks, tests, mutation gates, derived-count check and production dependency audit, rather than treating format/build/lint as the complete gate. For a specifically limited check, run that scope and state what remains unchecked.
- Use npm run counts:check for maintained counts and documentation declarations. Counting occurrences of a word in README does not validate a claim; compare other relevant claims with source or measured output.
- Match the CI dependency audit scope: currently npm audit --audit-level=high --omit=dev. Distinguish a requested broader development-dependency audit.
- Check tracked internals with git ls-files and the current .gitignore. tools/agent-skills/ is the versioned skill source; .agents/ and .claude/ contain ignored local installations. Check the catalog and synchronization rather than force-adding installed copies. Judge .codex/, .mcp.json and memory-bank/ from current repository policy and tracking rather than a blanket exclusion.
- Run temporary-source mutation gates separately from format/lint/build checks so transient fixtures do not contaminate results.
- Do not run repository-wide formatting to repair unrelated concurrent edits.
Report actual commands, failures, unavailable checks and relevant dirty files. Preserve the distinction between a check that passed, one that failed, and one that never ran.
When available, dev:map checks configured dependency boundaries and visualizes static module/IPC scope. Inspect unresolved edges and graph limitations; do not infer complete architecture coverage. dev:security runs pinned local Semgrep rules with strict parser handling. Zero findings with parser errors is an incomplete check, not a pass. Read the JSON error/skip list before reporting success.
Use the available Codex Security diff workflow for a security review of a patch; a whole-repository scan or repeated deep scan belongs to an explicitly scoped audit. Protect credentials and telemetry when querying external documentation tools. Keep fresh verification receipts separate from an agent's narrative; the narrative does not prove a check ran. Development/Electron dependencies are outside an npm audit --omit=dev result.
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.
- today First seen · 23 lines · 30 tokens per session scan A 73f867dc4187
audit-check is a skill published in the GitHub repository antropos17/Aegis (157 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 523 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 2026-10-17.
Other skills, from other repositories
fix-ci
Fix the failed CI checks for the current session. Use when the user requests a CI fix via the Fix Checks button in the Changes toolbar.
analyzing-github-ci-performance
Computes a CI/CD metrics table from raw GitHub Actions records for one repository over the last 30 days, including failure rates and developer waiting time. Use for historical CI performance questions or the first-experience repository demo. For currently failing checks, use reporting-github-ci-failures.
repair-github-ci
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
scheduling-github-ci-repairs
Sets up ongoing local monitoring of one repository's open pull requests, automatically editing, testing, and pushing fixes for failing GitHub Actions checks. Offers a disposable private-repository demonstration. Use for recurring PR repair or the local CI onboarding demo.
delegating-github-ci-repairs
In the interactive shell, prepare the hosted gateway and delegate a bounded GitHub PR repair or remote demo. Use for remote CI repair onboarding.
analyzing-local-repositories
Shows what the user's local repositories say about how they work, read from git and CI files on this machine with no GitHub token or network: follow-up fixes, CI trial and error, AI co-authorship, workflow hygiene, tests and loose ends. Use when GitHub is not connected or cannot be read during onboarding, when the…