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/tinoimammp/vantage-security-agent/fix-diffgit clone --depth 1 https://github.com/tinoimammp/vantage-security-agentWrote 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/tinoimammp/vantage-security-agent/fix-diff)<a href="https://agentmods.dev/commands/tinoimammp/vantage-security-agent/fix-diff"><img src="https://agentmods.dev/badge/commands/tinoimammp/vantage-security-agent/fix-diff.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 | $0.00031 | $0.00659 |
| Opus 5 | $0.00015 | $0.00329 |
| Sonnet 5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
fix-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
This command modifies source code in the current repository. Unlike
every scan command, this is destructive by design — review the result with
git diff before committing. This is /vantage:fix-issue's counterpart for
findings from /vantage:scan-diff instead of a full pipeline run.
Fix finding $ARGUMENTS (expects two values: a commit-scan id — the commit
hash, or pr-<number>/mr-<number> — then a finding id like F-001)
against the current project.
- If either value is missing, stop and ask for both — do not guess which
commit-scan or finding to fix. If the commit-scan id is unknown, list the
existing ones by listing
./.vantage/artifacts/commit-scans/*/directory names. - Read
./.vantage/artifacts/commit-scans/<commit-scan-id>/validated-findings.json. Find the entry with thisid.- File or entry not found → stop, report that it doesn't exist (check the
commit-scan id and finding id, or re-run
/vantage:scan-diff <commit-scan-id>first). - Found but
validated: false→ stop, report that only validated findings can be fixed. ./.vantage/artifacts/commit-scans/<commit-scan-id>/fixes/<id>.mdalready exists → stop, report it's already been addressed — don't re-apply.
- File or entry not found → stop, report that it doesn't exist (check the
commit-scan id and finding id, or re-run
- Dispatch
fix-agentvia Task for this one finding (${CLAUDE_PLUGIN_ROOT}/agents/others/fix-agent.md), telling it explicitly to read the finding fromartifacts/commit-scans/<commit-scan-id>/validated-findings.json(not the main pipeline's file) and, if present,artifacts/commit-scans/<commit-scan-id>/poc/<id>.md. It re-locates the vulnerable pattern in the current source (it may have moved), and applies the minimal targeted edit implementing theremediation— or marks itnot_auto_fixablewith a reason if a safe automated edit isn't possible. - Confirm
./.vantage/artifacts/commit-scans/<commit-scan-id>/fixes/<id>.mdwas written, and append the result to./.vantage/artifacts/run-log.md.
Report which file(s) changed (or why the fix was skipped), and remind the
user that fix-agent never runs a build or test suite — they must review
the diff and run their own tests before committing.
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 · 46 lines · 31 tokens per session scan A 5cbf596de743
fix-diff is a command published in the GitHub repository tinoimammp/vantage-security-agent (4 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 659 once invoked, about $0.0002 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
review-cheatsheet-pr
Aggressively review an OWASP cheat sheet PR across security, practicality, links/sources, duplication, and language; produce a single MERGE/REQUESTCHANGES/CLOSE verdict.
scope
Prepare a focused analysis scope for large codebases or monorepos using repomix. Creates a digestible snapshot of the target code for subsequent security analysis.
threats
Combines application understanding with systematic threat identification. First understands the application, then identifies what could go wrong.
scan
Run automated static analysis and write the results to .claude/findings.json.
propagate
When you find one vulnerability, search for the same pattern everywhere else. Developers often make the same mistake repeatedly.
mobile-audit
End-to-end mobile audit driver for Android targets. Most Android bug-bounty work involves a decompiled APK that's been split into two directories.