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 OutlineDriven/outline-driven-development --skill audit-projectgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/audit-project)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/audit-project"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/audit-project/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/outlinedriven/outline-driven-development/audit-project"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/audit-project.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 | $0.00041 | $0.05464 |
| Opus 5.5 | $0.00016 | $0.02186 |
| Sonnet 5.5 | $0.00008 | $0.01093 |
| Haiku 4.5 | $0.00004 | $0.00546 |
Grade B, and why
audit-project scanned grade B with 1 finding 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 24d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `devops`: CI gaps (tests not run, wrong paths ignored, cache poisoning, unpinned risky actions/images, missing required gates); secret handling (secrets printed, available to untrusted PRs, copied into images, in env e Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit project
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user says "audit my code", "find all the bugs", "deep code audit", "review until clean", or "grill my changes". |
| Authority | Reversible local: writes only .outline/audit/ queue state, per-iteration JSON, minimal fix batches to VCS-tracked files in the resolved scope, and optionally TECHNICAL_DEBT.md; rollback is version control (git restore -- <files> or git revert HEAD --no-edit with the persisted queue). No remote mutation. No push, no reset --hard, no git clean. |
| Side effect | Writes local audit queue state and applies local fix batches; may emit TECHNICAL_DEBT.md. |
| Done | Zero open findings at or above the severity floor after consolidation and re-review, or a user decision gate chosen, or the iteration cap reached, with scope, selected reviewers, iterations, fixes, verification commands, regressions, and queue path reported. |
Inputs
scope: path, glob, package, PR/diff, or.. Default..--recent: audit files touched in the last five commits plus unstaged/staged changes.--domain <reviewer>: run one reviewer domain only; the same consolidation contract still applies.--quick: single review pass; no fixes, no iteration.--resume: load.outline/audit/queue.jsonif present.--max-iterations N: default5; an explicit value overrides the scope-adaptive cap (5 to 15 based on change-set complexity).--severity-floor <critical|high|medium>(optional): terminating floor; defaulthigh(critical and high).mediumincludes medium findings in the fix queue.--against <ref>(optional): explicit base-ref override for diff resolution. Default: the merge-base of the current branch and its upstream.- State files (written, not supplied):
.outline/audit/queue.jsonand.outline/audit/iterations/<n>.json. caps(derived, not supplied):maxIterations(outer loop),fixAttemptCap(total fix attempts, 20 to 80),attemptsPerItem(per-item attempts, 3 to 5). Persisted to the queue.
What ships with it
3 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.
- 24d ago Changed · +6 lines ed3c1b0f7ae9
- 1mo ago Changed · -28 tokens per session a02e26d0f195
- 1mo ago First seen · 124 lines · 69 tokens per session scan B 1337e9dac5ae
audit-project is a skill published in the GitHub repository OutlineDriven/outline-driven-development (53 stars, last pushed 22d ago), licensed Apache-2.0. It adds 41 tokens to every session and 5,464 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
karpathy-guidelines
Surgical execution guardrails for coding, debugging, review, and refactor tasks.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
time-bomb-radar
Finds deferred operations that crash on aged data -- code that passes every test but breaks weeks or months after release. Covers cascade deletes, cache expiry, trial paths, background accumulation, date-threshold transitions, and scheduled side effects. Triggers: "time bomb", "time-bomb", "/time-bomb-radar", "aged…
code-review
A method for reviewing code, bugs, diffs, branches, and pull requests. A diff is the set of changes between two versions of code, and a pull request is a proposed change submitted for review.