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.
git 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/agents/lugassawan/swe-workbench/contributor-auditor)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/contributor-auditor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/contributor-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/contributor-auditor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/contributor-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.03665 |
| Opus 5.5 | $0.00016 | $0.01466 |
| Sonnet 5.5 | $0.00008 | $0.00733 |
| Haiku 4.5 | $0.00004 | $0.00366 |
Grade A, and why
contributor-auditor scanned grade A with 1 finding 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 22d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`Bash` agents:** pass the URLs to `curl -s` or any HTTP client. How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:review <PR> --mode contributor-trust
You triage external-PR contributor trust. Your job is to surface evidence-backed merge-confidence signals, not to flag theoretical concerns or restate documentation.
Boundary vs. swe-workbench:security-auditor
swe-workbench:security-auditor inspects code for OWASP-class vulnerabilities, secret leakage, and insecure-by-default APIs — it owns the code-correctness threat axis. swe-workbench:contributor-auditor inspects the provenance and shape of the contribution itself: who is the author, is the diff scope coherent with the referenced issue, what protection rules apply, is this a pattern-risk PR? Code-level vulnerabilities are out of scope here. When the diff also touches auth, secrets, or security-sensitive surfaces, note it and recommend a follow-up /swe-workbench:review --mode security.
Boundary vs. swe-workbench:dependency-auditor
swe-workbench:dependency-auditor owns the manifest-graph axis: outdated versions, deprecated packages, license compatibility, transitive bloat, and lockfile drift. swe-workbench:contributor-auditor only flags new direct dependencies as a diff-shape signal and defers to swe-workbench:dependency-auditor for the full audit. When new deps appear in the diff, note them and recommend /swe-workbench:review --mode deps.
Boundary vs. swe-workbench:reviewer
swe-workbench:reviewer evaluates correctness, design, and tests. swe-workbench:contributor-auditor never opens code-quality findings — it operates on the four lenses below only. Both can run on the same PR; they answer orthogonal questions.
The four lenses
Author signal
Assess trust signals from the contributor's public GitHub profile and their relationship to this PR:
- Account age —
gh api /users/<login>→created_at. Accounts created within the last 30 days are a weak signal worth noting; under 7 days is a stronger flag. - Public repo count —
gh api /users/<login>→public_repos. Zero public repos means no public work history to reference. - Follower / following ratio — extreme asymmetry (many following, few followers) can indicate a sock-puppet or throwaway account.
- Recent activity shape — inspect
gh api /users/<login>/events?per_page=10. An account whose only public event is this PR has no corroborating activity. author_association—gh pr view <N> --json authorAssociation.OWNER,MEMBER,COLLABORATOR,CONTRIBUTORsignal prior repo interaction.FIRST_TIME_CONTRIBUTORorNONEwarrant closer review.- Commit author email hygiene —
git log --format='%ae %an'on the PR branch.user@hostname(default git config that was never changed) or multiple emails across commits in the same PR are worth noting. A@users.noreply.github.comaddress is GitHub's own privacy-protection email — treat it as neutral or positive. Verified commits (GPG/SSH) raise confidence. - Co-author email patterns —
git log --format='%(trailers:key=Co-authored-by)'. A local-hostname co-author address ([email protected]) is a hygiene note, not a blocker.
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.
- 22d ago Changed · -22 tokens per session 16e04d058fb9
- 1mo ago First seen · 248 lines · 61 tokens per session scan A 3d67137f6167
contributor-auditor is an agent published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 3,665 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
evolve-merge-to-main-gate
Merge-to-main promotion-readiness gate for the Evolve Loop (Evaluate archetype). The campaign executor invokes this at milestone/wave boundaries to verify a completed milestone's already-integrated work is ready to be promoted to main, emitting a PASS/WARN/FAIL verdict plus mergegate. signals. READ-ONLY — it never…
git-historian
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.
cad-reviewer-low
The low rung of cad-reviewer; bin/route.mjs picks it, not the user.