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 ai-driven-dev/framework --skill 04-auditgit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/04-audit)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/04-audit"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/04-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/ai-driven-dev/framework/04-audit"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/04-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 Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00054 | $0.00606 |
| Opus 5.5 | $0.00022 | $0.00242 |
| Sonnet 5.5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
04-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 5d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: audit
Diagnose a codebase against quality pillars and emit one ranked findings report. Read-only: it identifies and ranks problems, never changes code.
Actions
| # | Action | Pillar | Lens |
|---|---|---|---|
| 01 | code-quality |
code-quality | Clean code (naming, SOLID, DRY, readability, smells) and tech debt (dead code, complexity, file/function size, error handling) |
| 02 | architecture |
architecture | Conformance to C4 / ADRs, coupling, boundaries, layering |
| 03 | security |
security | OWASP risks, authz, input validation, secrets in code |
| 04 | dependencies |
dependencies | CVEs, licenses, outdated and unused deps, supply chain |
| 05 | performance |
performance | N+1 queries, hot paths, bundle size, heavy operations |
| 06 | tests |
tests | Critical-path coverage, flakiness, test pyramid balance |
| 07 | ui |
ui | Loading/error/empty states, visual hierarchy, design-system drift, responsive, a11y |
Run the one pillar named, or offer all seven when the request is unscoped.
Before running an action, read its file in actions/, not only the table or assets.
Transversal rules
- Read-only: diagnose and rank, never edit code.
- Scope: run the one named pillar, or for an unscoped request ask once "all seven pillars, or one?" before running. Never silently default to one pillar, never blind-run all without offering the choice.
- One folder per run,
aidd_docs/tasks/<yyyy_mm>/<yyyy_mm_dd>_audit/, like a feature folder. Every pillar that runs always writes its own<pillar>.mdthere, alone or in a full run. A full run additionally writes a mergedreport.md: one Findings table (category = pillar, severity-first), one Top-actions list, and one Coverage section over all seven pillars. - Unscannable pillar: skip it, record it under
Coverage > Skippedwith the reason, and never invent findings for it. - Every finding row carries a severity, its pillar, a concrete
file:line, the issue, a suggested fix, and an effort.
What ships with it
8 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.
- 5d ago Changed · -1 lines d0bf198fda06
- 1mo ago First seen · 38 lines · 54 tokens per session scan A f14dddb4226c
04-audit is a skill published in the GitHub repository ai-driven-dev/framework (524 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 606 once invoked, about $0.0002 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
error-recovery
A guide to detecting and recovering from failures in long-running AI agents. It covers API outages, bad tool calls, broken conversation state, stalled streams, repeated loops, retries, fallback models, and circuit breakers that stop repeated failure.
doctor
Diagnose and repair your TinyFish setup — MCP registration, auth, and connectivity. Runs the TinyFish CLI's own doctor for the config checks, then does the one thing the CLI cannot — proving this harness can actually reach TinyFish. Run when TinyFish tools fail, return auth errors, or after an install that did not…
feedback
File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report. Creates a GitHub issue on tinyfish-io/tinyfish-cookbook with the user's approval; nothing is sent without an explicit preview.
code-search
Search a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.
ci-troubleshoot
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and retrigger jobs. Use when a CI run is red, a release is stuck, a workflow won't dispatch, or you need to know which workflow does…
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…