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 skills add lugassawan/swe-workbench --skill workflow-codebase-auditgit 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/skills/lugassawan/swe-workbench/workflow-codebase-audit)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-codebase-audit"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-codebase-audit/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/skills/lugassawan/swe-workbench/workflow-codebase-audit"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-codebase-audit.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 | $0.00091 | $0.01880 |
| Opus 5.5 | $0.00036 | $0.00752 |
| Sonnet 5.5 | $0.00018 | $0.00376 |
| Haiku 4.5 | $0.00009 | $0.00188 |
Grade A, and why
workflow-codebase-audit 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 23d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Codebase Audit (cold-start multi-domain sweep)
Announce at start: "Activating swe-workbench:workflow-codebase-audit to run the cold-start audit sweep."
When to invoke
- Take-home or technical assessment requiring a broad codebase review.
- Post-acquisition or due-diligence review of an unfamiliar repo.
- Inherited-service onboarding: "I just took ownership of this, what's the state of it?"
- Pre-refactor tech-debt sweep across a monorepo or service.
When NOT to invoke
- Single-domain security audit → use
swe-workbench:security-auditordirectly (depth-first, OWASP-focused). - Known bug with a repro → use
/swe-workbench:debug(root-cause + fix lifecycle). - PR diff review → use
/swe-workbench:revieworswe-workbench:workflow-pr-review. - Code already familiar; you know what to look for → run targeted tools directly.
Composition
This skill orchestrates; domain analysis is delegated to:
swe-workbench:auditorsubagent — broad multi-domain sweep (security, perf, reliability, tooling, testing, dead-code).swe-workbench:security-auditorsubagent — depth-first CVE + threat review; deep mode only, top-N security findings.swe-workbench:debuggersubagent — root-cause + fix path on top-N reliability findings by rank; deep mode only.swe-workbench:ticket-contextskill — prepended when a ticket ref is present in$ARGUMENTS.
Phases
Phase 1 — Clarify (only when --scope is absent)
Skip this phase entirely if --scope appears explicitly in $ARGUMENTS — including --scope=all, which means "all domains, no clarification needed."
Only when --scope is completely absent: ask the user which domains matter most (security, perf, reliability, tooling, testing, dead-code), then proceed. If superpowers:brainstorming is available, invoke it to surface assumptions about the codebase before sweeping. If unavailable, ask directly: "Which audit domains do you want covered? (security, perf, reliability, tooling, testing, dead-code — or all?)"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago Changed 9aad1468f842
- 1mo ago First seen · 127 lines · 91 tokens per session scan A e61d8017ac82
workflow-codebase-audit is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 1,880 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
bug-fix
Investigate, reproduce, and safely fix a bug with regression protection. Composes context, diagnosis, architecture, code quality, and testing guardrails into a reproduce-first repair workflow. Use when the user says 'fix this bug', 'debug this', 'investigate this failure', 'patch this regression', 'repair this issue'…
refactor-safely
Restructure existing code safely without changing externally observable behavior. Composes context, design, architecture, code quality, and testing guardrails into a characterization-first refactoring workflow. Use when the user says 'refactor this', 'clean this up', 'untangle this module', 'move this to the right…
functions-development
Build serverless Go or Python functions for Falcon Foundry apps. TRIGGER when user asks to "create a function", "write a serverless function", "build backend logic", runs foundry functions create, or needs help with FDK handler patterns, function testing, or collection integration from functions. Also TRIGGER when…
understand-codebase
Build an evidence-backed map of an unfamiliar repository with the ai-architect code graph. Use before implementing a feature, debugging an unfamiliar subsystem, explaining architecture, or making structural claims about symbols and dependencies.
golang-benchmark
Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with…
golang-troubleshooting
Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve debugger, race detection, GODEBUG tracing, and production…