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 wiolett-industries/marketplace --skill audit-flowgit clone --depth 1 https://github.com/wiolett-industries/marketplaceWrote 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/wiolett-industries/marketplace/audit-flow)<a href="https://agentmods.dev/skills/wiolett-industries/marketplace/audit-flow"><img src="https://agentmods.dev/badge/skills/wiolett-industries/marketplace/audit-flow/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/wiolett-industries/marketplace/audit-flow"><img src="https://agentmods.dev/badge/skills/wiolett-industries/marketplace/audit-flow.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 | $0.00068 | $0.00802 |
| Opus 5.5 | $0.00027 | $0.00321 |
| Sonnet 5.5 | $0.00014 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
audit-flow 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 2mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Flow
Produce evidence-backed findings without editing the audited code. An audit is one primary path; do not add finalizing-plan or implementation unless the user separately requests fixes.
Select Depth And Output
quick: bounded question, small diff, or ordinary analysis; parent works locally, writes no.workflowartifacts, launches 0 agents, and reports in chat.standard: one coherent subsystem or review question; use 1 scoped reviewer by default when the question crosses several surfaces, has a plausible regression/risk that benefits from an independent read, or would otherwise overload the parent context. Keep a small direct diff or single-surface question local. Create a durable run only when requested or needed for later planning/recovery.deep: several genuinely independent risk domains; create a durable run and use at most 2 scoped reviewers when the benefit gate passes.exhaustive: explicit broad/high-risk request only; create a durable run and declare a task-wide budget, default maximum 4. Exceed it only with explicit approval.
Repository size, file count, checklist length, or number of possible lenses does not raise depth. Read-only/no-edits requests use quick chat output unless the same request explicitly authorizes audit artifacts.
Scope And Evidence
Define the target, included/excluded paths, audit questions, non-goals, depth, and evidence standard. Inspect the real source of truth. Every material finding needs a file/line, command/output, runtime observation, or other reproducible evidence.
Agents are read-only and consume the declared audit budget. Group overlapping domains. Use workflow_audit_reviewer for independent evidence that changes confidence or coverage; nontrivial diagnosis and review are affirmative candidates, not exceptions. Do not assign one agent per file, prompt, or gate.
Durable Audit Path
When a durable run is authorized, use workflow_audit_create, workflow_audit_update, workflow_audit_artifact_write, workflow_findings_normalize, workflow_handoff_write, and workflow_audit_complete. Manual state/artifact writes are fallback only.
What ships with it
1 file 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.
- 2mo ago First seen · 50 lines · 68 tokens per session scan A 11eeb888f23b
audit-flow is a skill published in the GitHub repository wiolett-industries/marketplace (10 stars, last pushed 15d ago), licensed MIT. It adds 68 tokens to every session and 802 once invoked, about $0.0003 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 2026-08-30.
audit-flow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-flowwiolett-industries/marketplace | Skill | 10 | 15d ago | MIT | A | 68 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |