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 danygiguere/audit-skills --skill auditgit clone --depth 1 https://github.com/danygiguere/audit-skillsWrote 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/danygiguere/audit-skills/audit)<a href="https://agentmods.dev/skills/danygiguere/audit-skills/audit"><img src="https://agentmods.dev/badge/skills/danygiguere/audit-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/danygiguere/audit-skills/audit"><img src="https://agentmods.dev/badge/skills/danygiguere/audit-skills/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 | $0.00051 | $0.01534 |
| Opus 5 | $0.00026 | $0.00767 |
| Sonnet 5 | $0.00010 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit procedure
The audit target is whatever the user specified; if nothing was specified, default to the current diff (uncommitted changes, or the branch's changes against the default branch). If there is no diff either, ask what to audit rather than picking a scope yourself.
- Identify what the code under audit does. Trace the data flow: what
inputs arrive, what is looked up, what is written, what is rendered or
returned, what runs async. If the target is larger than a diff — a
module, service, or whole repo — load
references/methodology/scope.mdfirst and follow its inventory, ranking, and budget procedure. - Load only the checklist files matching that behavior, from the map below.
- Check each invariant in the loaded files against the code.
- Verify before reporting: load
references/methodology/verify.mdand run every candidate through it — name the attacker and the victim, hunt for existing mitigations in the surrounding code (middleware, base classes, decorators, callers), and when auditing a diff, anchor each finding to the lines that introduce or enable it. A candidate survives only if you cannot refute it with cited evidence. - Report each finding with: severity (assigned per
references/methodology/severity.md),file:line, the violated invariant, and a one-line fix direction. Say explicitly which checklists were applied and came back clean. - Fix only on request: when the user asks for remediation, load the
matching
references/remediation/file and apply its patterns.
Do not manufacture findings for topics that don't apply (e.g., CSRF on a token-authenticated API, tenant isolation in a single-tenant app).
What to load
Paths relative to this skill's directory. Load every row that matches; skip the rest.
| The code… | Read |
|---|---|
| Gates actions by role, permission, or ownership | references/access-data-security/authorization.md |
| Handles login, logout, reset, tokens, sessions | references/access-data-security/authn-session.md |
| Verifies JWTs, API keys, signed URLs, or webhook signatures | references/access-data-security/token-validation.md |
| Fetches/mutates a resource by an ID from the request | references/access-data-security/idor.md + references/access-data-security/authorization.md |
| Serializes models, formats errors, writes logs | references/access-data-security/data-exposure.md |
| Hashes, encrypts, generates or compares secrets | references/access-data-security/crypto-data-protection.md |
| Renders user data into HTML/JS/URLs/headers/emails | references/access-data-security/output-encoding.md |
| Touches data or caches in a multi-tenant app | references/access-data-security/tenant-isolation.md |
| Changes state with cookie/session-based auth | references/access-data-security/csrf.md |
| Binds request payloads onto models/entities | references/access-data-security/mass-assignment.md |
| Builds queries/commands/templates/paths from input | references/input-api-dependency/injection.md |
| Deserializes untrusted bytes (sessions, caches, queues, uploads) | references/input-api-dependency/deserialization.md |
| Configures CORS, headers, cookies, debug, env | references/input-api-dependency/config.md |
| Touches API keys, credentials, tokens | references/input-api-dependency/secrets.md |
| Validates (or should validate) request input | references/input-api-dependency/api-contract-validation.md |
| Accepts, stores, processes, or serves files | references/input-api-dependency/file-handling.md |
| Makes network requests to user-influenced URLs | references/input-api-dependency/ssrf.md |
| Adds validators, regexes, allowlists, or parsing | references/input-api-dependency/parser-differentials.md |
| Writes to multiple tables/stores/systems at once | references/correctness/atomicity.md |
| Handles payments, webhooks, retries, emails | references/correctness/idempotency.md |
| Runs jobs, scheduled tasks, or queue consumers | references/correctness/background-work.md |
| Shares mutable state, caches, counters | references/correctness/state-management.md |
| Reads or writes assuming a query matches exactly one row | references/correctness/cardinality.md |
| Computes money, totals, taxes, splits, or rounding | references/correctness/numeric-precision.md |
| Stores or computes timestamps, durations, timeouts, expiry | references/correctness/time-clock.md |
| Catches/throws errors, maps errors to HTTP statuses | references/correctness/exception-handling.md |
| Creates promises, futures, tasks, or publishers | references/correctness/discarded-async.md |
| Loads related data inside a loop over a collection | references/operability/nplus1.md |
| Adds endpoints/jobs, handles errors | references/operability/observability.md |
| Changes database schema | references/operability/migration-safety.md + references/operability/schema-design.md |
| Does work proportional to input size | references/operability/resource-limits.md |
| Runs async/await, event-loop, or coroutine code | references/operability/blocking-io-async.md |
| Is meant to scale out / run as multiple replicas | references/operability/statelessness.md |
| Caches values, responses, or computed results | references/operability/caching.md |
| — Scoping a target larger than a diff (step 1) | references/methodology/scope.md |
| — Verifying candidate findings (step 4, always) | references/methodology/verify.md |
| — Rating finding severity (step 5, always) | references/methodology/severity.md |
| — Fixing confirmed findings | references/remediation/authz-patterns.md, references/remediation/async-patterns.md, references/remediation/observability-patterns.md |
What ships with it
41 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.
- references/access-data-security/authn-session.md 5.7 KB
- references/access-data-security/authorization.md 5.8 KB
- references/access-data-security/crypto-data-protection.md 5.1 KB
- references/access-data-security/csrf.md 4.9 KB
- references/access-data-security/data-exposure.md 5.0 KB
- references/access-data-security/idor.md 4.4 KB
- references/access-data-security/mass-assignment.md 4.9 KB
- references/access-data-security/output-encoding.md 4.9 KB
- references/access-data-security/tenant-isolation.md 5.2 KB
- references/access-data-security/token-validation.md 7.3 KB
- references/correctness/atomicity.md 4.8 KB
- references/correctness/background-work.md 5.2 KB
- references/correctness/cardinality.md 5.7 KB
- references/correctness/discarded-async.md 5.7 KB
- references/correctness/exception-handling.md 6.5 KB
- references/correctness/idempotency.md 5.3 KB
- references/correctness/numeric-precision.md 5.6 KB
- references/correctness/state-management.md 5.4 KB
- references/correctness/time-clock.md 6.3 KB
- references/input-api-dependency/api-contract-validation.md 5.7 KB
- references/input-api-dependency/config.md 5.6 KB
- references/input-api-dependency/deserialization.md 6.0 KB
- references/input-api-dependency/file-handling.md 5.7 KB
- references/input-api-dependency/injection.md 5.5 KB
- references/input-api-dependency/parser-differentials.md 5.5 KB
- references/input-api-dependency/secrets.md 5.3 KB
- references/input-api-dependency/ssrf.md 6.0 KB
- references/methodology/scope.md 2.7 KB
- references/methodology/severity.md 2.6 KB
- references/methodology/verify.md 3.0 KB
- references/operability/blocking-io-async.md 5.1 KB
- references/operability/caching.md 5.8 KB
- references/operability/migration-safety.md 5.6 KB
- references/operability/nplus1.md 5.4 KB
- references/operability/observability.md 5.5 KB
- references/operability/resource-limits.md 5.9 KB
- references/operability/schema-design.md 6.1 KB
- references/operability/statelessness.md 5.8 KB
- references/remediation/async-patterns.md 7.4 KB
- references/remediation/authz-patterns.md 5.6 KB
- references/remediation/observability-patterns.md 6.3 KB
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.
- 12d ago First seen · 88 lines · 51 tokens per session scan A fb1109e912f9
audit is a skill published in the GitHub repository danygiguere/audit-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,534 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pr-review
AUTHOR SKILL (internal to microsoft/aspire-skills). Reviews pull requests into this repo for problems only — bugs, regressions, missing eval coverage, frontmatter or routing damage, plugin-manifest drift, hook safety, and other concrete issues. Drives a six-step workflow: identify the PR, ensure the branch is…
release-habit-hooks
Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands, enforces the in-sync versioning rule, validates the changelog, and drives the tag-triggered PyPI publish.
habit-hooks-review
Spawn a reviewer sub-agent to assess a change set against habit-hooks's coding principles. Use AFTER habit-hooks reports clean — habit-hooks catches structural smells; this catches what it cannot (correctness, tests, design, missed edge cases).
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
software-code-review
Evaluate source code for correctness, quality, security, style conformance, and maintainability, producing a structured review report with findings and recommendations. Use when the user wants to review, critique, audit, evaluate, or inspect source code — checking for bugs, logic errors, unhandled error paths…
audit-round
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE…