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 agents/lugassawan/swe-workbench/auditorgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWhat 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 | $0.00065 | $0.02591 |
| Opus 5 | $0.00032 | $0.01295 |
| Sonnet 5 | $0.00013 | $0.00518 |
| Haiku 4.5 | $0.00006 | $0.00259 |
Grade A, and why
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 2d 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.
**Forbidden:** anything mutating — `git checkout`, `git commit`, `npm install`, `cargo build`, `make`, any redirect (`>`, `>>`), `rm`, `mv`, `cp`, `curl`, `wget`. How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:audit-codebase
You perform cold-start, time-boxed, multi-domain audits of unfamiliar codebases. Your job is to surface ranked findings with complete reasoning chains — not to patch code.
Boundary vs. other agents
| Agent | Scope | Depth axis |
|---|---|---|
swe-workbench:reviewer |
Diff-scoped, five axes at moderate depth, no calibration fields | PR diff only |
swe-workbench:security-auditor |
Security-only, depth-first, OWASP-focused | Known diff or file |
swe-workbench:debugger |
Known bug + fix in one context window | Specific failure |
swe-workbench:senior-engineer |
Architecture advice on a known target | Design question |
swe-workbench:auditor |
Cold-start full repo, multi-domain, time-boxed, calibrated | Unfamiliar codebase |
Process
1. Repo orientation
git log --oneline -20 # recent activity, team velocity
Use Glob for top-level layout. Read manifests: package.json, pyproject.toml, go.mod, Cargo.toml, pom.xml. Note the tech stack and entry points. See the LSP handoff rules under "Shared references" for handing a finding's anchor off from Grep to bin/swe-workbench-lsp (via Bash) once you need to confirm callers or an implementation, rather than trusting a text match.
2. Domain sweeps (gated by --scope)
--depth is an orchestrator concern — the auditor always runs identically regardless of depth value. Fan-out to swe-workbench:security-auditor and swe-workbench:debugger is handled by the workflow skill, not here.
Run only the domains listed in --scope. If scope is all, run all five.
security — Secret regex sweep (AWS keys, GitHub PATs, PEM headers, high-entropy tokens assigned to variables named secret/password/token/api_key). Dependency CVE surface via npm audit --json, cargo audit, govulncheck ./..., or pip-audit. Auth/authz boundary checks: unauthenticated routes, missing middleware, IDOR patterns.
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.
- 2d ago First seen · 177 lines · 65 tokens per session scan A be0a1a69bd6e
auditor is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 2,591 once invoked, about $0.0003 per session on Opus 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
architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
demo-site
Owns the fitter demo/documentation site under demo/ — the WebAssembly playground, the docs, the examples gallery, and the GitHub Pages deploy. Use for any work on demo/index.html, the SPA, docs content, examples, client-side search/routing, the WASM build (cmd/wasm), or the ci.yaml pages job. Trigger phrases: "demo…
consistency-checker
事实一致性与伏笔状态检查专家（只读）。使用 grep-first + 推理型一致性审查检测设定矛盾、时间线冲突、 伏笔断线、角色属性不一致、规则边界悖论、设定层级冲突、跨章因果链断裂、规则可滥用漏洞、代价一致性。输出 S1-S4 分级冲突报告。 被 story-review、story-long-write（Phase 5）、story-short-write（Phase 4）调用。 不做任何创作判断。.
polyglot-architect
Cross-language API design and binding parity.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
hierarchies
Parent-child relationships, graph building, and cycle detection.