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/lugassawan/swe-workbench/security-reviewgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/security-review)<a href="https://agentmods.dev/commands/lugassawan/swe-workbench/security-review"><img src="https://agentmods.dev/badge/commands/lugassawan/swe-workbench/security-review.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 | $0.00043 | $0.00365 |
| Opus 5 | $0.00022 | $0.00182 |
| Sonnet 5 | $0.00009 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
security-review 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 5d 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
Target: $ARGUMENTS
If $ARGUMENTS contains a ticket reference, invoke swe-workbench:ticket-context first and prepend its summary to the delegation context. (Trigger patterns are defined in that skill's "When to invoke" section.)
Delegate to the swe-workbench:security-auditor subagent with the resolved diff (PR diff via gh pr diff <N> if $ARGUMENTS is a PR number — stripping a leading # if present; otherwise the local-diff cascade: git diff → git diff --staged → git diff origin/main...HEAD). Ask for a prioritized findings report.
Output
The swe-workbench:security-auditor subagent produces a severity-organized findings report. Expect:
- Critical — data exfiltration, authentication bypass, direct secret exposure, remote code execution risk.
- High — exploitable injection (SQLi, XSS, SSRF, XXE), broken access control, insecure deserialization.
- Medium — missing input validation at trust boundaries, insecure defaults, weak cryptographic choices.
- Low — defence-in-depth gaps, minor information-disclosure risks, dependency CVEs with low exploitability.
Each finding uses: Severity | File:Line | Issue | Why it matters | Suggested fix. The report closes with a short summary section (total counts by severity, surface areas touched, recommended next action).
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.
- 5d ago First seen · 22 lines · 43 tokens per session scan A 30cfe5b7849b
security-review is a command published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 365 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
brooks-debt
Run a Brooks-Lint tech debt assessment.
brooks-review
Run a Brooks-Lint PR code review.
brooks-sweep
Run all Brooks-Lint analyses in one pass, auto-fix safe findings, confirm risky ones.
new-route
Scaffold a new API route end-to-end in the Go backend.
integrity
Fast integrity check on the current work. Feynman-style: what could invalidate this?
pr
Create a pull request with zetetic-standard review and documentation.