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 aAAaqwq/AGI-Super-Team --skill agent-skills-auditgit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-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/aaaaqwq/agi-super-team/agent-skills-audit)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/agent-skills-audit"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agent-skills-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/aaaaqwq/agi-super-team/agent-skills-audit"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agent-skills-audit.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 | $0.00081 | $0.00924 |
| Opus 5 | $0.00041 | $0.00462 |
| Sonnet 5 | $0.00016 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
audit-code 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Code
Overview
Run an expert-panel audit with strict sequencing and one unified output document. Produce findings first, sorted by severity, with file references, exploit/perf/flow impact, and actionable fixes.
Load references/audit-framework.md before starting the analysis.
Required Inputs
Collect or infer the following:
- Audit scope: paths, modules, PR diff, or whole repository.
- Product context: PRD/spec/user stories, trust boundaries, and critical business flows.
- Runtime context: deployment model, queue/cron/background jobs, traffic profile, data sensitivity, and abuse assumptions.
- Constraints: timeline, acceptable risk, and preferred remediation style.
If product context is missing, state assumptions explicitly and continue.
Team Roles
Use exactly these roles:
- Security expert
- Performance expert
- UX expert
- DX expert
- Edge case master
- Tie-breaker team lead
The tie-breaker lead resolves conflicts, prioritizes issues, and produces the final single report.
Workflow
Follow this sequence every time:
-
Build Context Read code + product flows. Identify assets, entry points, high-risk operations, privileged actions, external dependencies, and "failure hurts" journeys.
-
Build Invariant Coverage Matrix Before specialist pass 1, map critical invariants to every mutating path (HTTP routes, webhooks, async jobs, scripts):
- Data-link invariants: multi-table relationships that must remain consistent.
- Auth lifecycle invariants: disable/revoke semantics for sessions/tokens/API keys.
- Input/transport invariants: validation, content-type policy, body-size/parse behavior.
- Shape invariants: trees/graphs must reject cycles where applicable. Treat missing parity across equivalent paths as a finding candidate.
- Pass 1 Specialist Reviews Run role-specific analysis in this order:
- Security
- Performance
- UX
- DX
- Edge case master
Capture findings using the schema in
references/audit-framework.md.
- Tie-Breaker Reconciliation Resolve disagreements:
- Decide whether contested items are true issues.
- Set severity and confidence.
- Remove duplicates and merge overlapping findings.
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 First seen · 116 lines · 81 tokens per session scan A a494a288a919
audit-code is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 924 once invoked, about $0.0004 per session on Opus 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
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
flo-simplify
Review changed code for reuse, quality, and efficiency, then fix any issues found. Sizes review effort to the diff — trivial edits get a self-review, substantial edits get parallel agents. Renamed from /simplify to avoid collision with Claude Code's built-in simplify skill.
pr-feedback
Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.
aigon-feature-code-review
Review feature - code review with fixes by a different agent.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.