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 agentmods add commands/sembraniteam/claude-plugins/audit-verifygit clone --depth 1 https://github.com/sembraniteam/claude-pluginsWrote 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/commands/sembraniteam/claude-plugins/audit-verify)<a href="https://agentmods.dev/commands/sembraniteam/claude-plugins/audit-verify"><img src="https://agentmods.dev/badge/commands/sembraniteam/claude-plugins/audit-verify.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00526 |
| Opus 5 | $0.00026 | $0.00263 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
audit-verify 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /audit-verify to independently verify security fixes without running the fixer again.
Step 1 — Gather inputs
Audit report
Check for an audit report in this order:
/audit,/audit-diff, or/audit-fileoutput in this session- A
SECURITY-AUDIT.mdfile in the current directory
If no audit report is found, say:
"No audit report found. Please point me to the original audit report file, or run
/audit(or/audit-difffor a PR-scoped scan) first to generate one."
Fix manifest
Check for a fix manifest from a previous /audit-fix run in this session.
If there is no manifest, ask:
"No fix manifest found from a previous
/audit-fixrun. Please describe which findings you've fixed and which files were changed (e.g., 'I manually fixed SA-001 in src/db.js and SA-002 in package.json'), and I'll verify those."
Accept the user's description and construct an informal manifest from it:
## Fix Manifest (user-provided)
| Finding-ID | File | Lines Changed | Summary |
|------------|----------------|----------------|----------------------------------|
| SA-001 | `src/db.js` | user-specified | Manual fix — parameterized query |
| SA-002 | `package.json` | user-specified | Manual version bump |
Step 2 — Run fix-reviewer
Spawn the fix-reviewer agent with:
- The audit report (from session or
SECURITY-AUDIT.md) - The fix manifest (from session, file, or constructed from user's description)
- Instruction to read the current state of all relevant files
Say: "Running independent verification of your fixes..."
Step 3 — Present results
Present the reviewer's full output to the user — all verdict blocks, the summary table, and the next-steps section. Do not filter or summarize.
After the reviewer's output, add:
"To target any remaining
partially-fixedornot-fixedfindings, run/audit-fix SA-NNNfor each one. If you fix them manually, run/audit-verifyagain."
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.
- 3d ago First seen · 52 lines · 51 tokens per session scan A 8a13c640402f
audit-verify is a command published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 526 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.