Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add allsmog/vuln-scout/plugin install vuln-scoutWrote 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/allsmog/vuln-scout/mutate)<a href="https://agentmods.dev/commands/allsmog/vuln-scout/mutate"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/mutate.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 5.1 | $0.00022 | $0.00508 |
| Opus 5 | $0.00011 | $0.00254 |
| Sonnet 5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
mutate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Security Mutation Testing
Identifies security controls (sanitizers, auth middleware, parameterized queries) in your code, temporarily removes them, and checks if the scanning pipeline detects the resulting vulnerability. Undetected mutations represent detection gaps in your security tooling.
Usage
/vuln-scout:mutate
/vuln-scout:mutate src/ --dry-run
Flags
| Flag | Effect |
|---|---|
path |
Directory to scan for mutations (default: current directory) |
--dry-run |
List possible mutations without applying them |
--format |
Output format: md or json |
Mutation Types
| Type | What It Removes |
|---|---|
remove-parameterization |
SQL parameter binding → string concatenation |
remove-auth-middleware |
Authentication middleware from route handlers |
remove-csrf-check |
CSRF token validation |
enable-shell |
Changes shell=False to shell=True in subprocess calls |
remove-sanitizer |
Input sanitization/validation function calls |
remove-rate-limit |
Rate limiting middleware |
Workflow
Step 1: Discover mutations
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/run_mutations.py" \
<path> \
--dry-run
Lists all security-weakening mutations found in the codebase.
Step 2: Test mutations (unless --dry-run)
For each mutation:
- Apply the mutation (replace the security control with the weakened version)
- Re-scan the mutated file with Semgrep
- Check if the mutation was detected as a vulnerability
- Revert the mutation
Step 3: Report
- Detected mutations: scanner caught the weakened code (good)
- Undetected mutations: scanner missed the vulnerability (detection gap)
- Kill rate: detected / total (higher is better)
Undetected mutations indicate places where removing a security control would go unnoticed by your scanning pipeline.
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.
- 8d ago First seen · 69 lines · 22 tokens per session scan A c090b9ca0ebc
mutate is a command published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 508 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
security-sast
Static Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
partition-dev
Derive test cases from Z specification using TTF testing tactics.
ccc-audit
Run npm audit + bundle size check + lint scan. Returns vulnerabilities, oversized bundles, and lint errors.
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.