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/allsmog/vuln-scout/diffgit clone --depth 1 https://github.com/allsmog/vuln-scoutWhat 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 | $0.00021 | $0.00461 |
| Opus 5 | $0.00010 | $0.00230 |
| Sonnet 5 | $0.00004 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
diff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Differential Security Analysis
Compare security findings between two git refs. Shows new vulnerabilities introduced, vulnerabilities fixed, and severity changes.
Usage
/vuln-scout:diff HEAD~5
/vuln-scout:diff v1.0.0 v2.0.0
/vuln-scout:diff main feature/auth --fail-on-regression
Flags
| Flag | Effect |
|---|---|
base-ref |
Git ref to compare against (required) |
head-ref |
Git ref to compare (default: HEAD) |
--tools |
Scanning tools to use (default: semgrep) |
--format |
Output format: md or json |
--fail-on-regression |
Exit 2 if regression score > 0 (more new findings than fixed) |
Workflow
Step 1: Scan baseline
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/run_diff.py" \
--base <base-ref> \
--head <head-ref> \
--tools <tools> \
--project-root .
The script handles git checkout, scanning both refs, and computing the diff.
Step 2: Display results
Show the diff report:
- New findings: vulnerabilities introduced since the baseline
- Fixed findings: vulnerabilities that no longer appear
- Changed findings: same location but different severity/verdict
- Regression score: positive = worse, negative = better
- New/removed endpoints: attack surface changes
Step 3: Exit code
0: no regression (fixed >= new, or--fail-on-regressionnot set)2: regression detected (with--fail-on-regression)
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 · 61 lines · 21 tokens per session scan A 385680feb629
diff is a command published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 461 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.
scan-diff
Scan only the changed files in a single commit or PR/MR for newly introduced vulnerabilities (fast incremental check, not a full pipeline run).
fix-diff
Apply a code-level fix for a finding from /vantage:scan-diff's commit/PR/MR scan — modifies the target repository's source code.
scan-mobile
Run the full mobile SAST pipeline (phases 01-06) against this repository — Android, iOS, React Native, or Flutter.
scan-web
Run the full web SAST pipeline (phases 01-06) against this repository.
fix-issue
Apply a code-level fix for one validated finding by id (e.g. F-001) — modifies the target repository's source code.