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 skills/lugassawan/swe-workbench/workflow-audit-emit-issuesnpx skills add lugassawan/swe-workbench --skill workflow-audit-emit-issuesgit 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-audit-emit-issues)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-audit-emit-issues"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-audit-emit-issues.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 5.1 | $0.00058 | $0.02273 |
| Opus 5 | $0.00029 | $0.01137 |
| Sonnet 5 | $0.00012 | $0.00455 |
| Haiku 4.5 | $0.00006 | $0.00227 |
Grade A, and why
workflow-audit-emit-issues 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 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.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workflow-audit-emit-issues
Files codebase audit findings as grouped GitHub issues — one issue per subsystem, sub-sectioned by domain.
When to invoke
After a codebase audit has produced a ranked findings table and the user accepts the
"File as issues?" offer emitted by the audit-codebase command. Requires ≥1 finding
in the orchestrator's context.
When NOT to invoke
- Zero findings — the audit ends at the rendered table; no offer is made.
- Without a preceding audit — this skill consumes in-context finding data only.
- To re-run the audit itself — see
swe-workbench:workflow-codebase-audit(read-only; no back-edge here).
Composition
This skill is the filing counterpart to (not a caller of) swe-workbench:workflow-codebase-audit.
Filing logic mirrors swe-workbench:workflow-bug-triage Phase 4 precedent: --body-file, .cmd
sidecar, preview-gate-then-confirm. Template and label discovery follows the same
chain used by agents/product-manager.md.
Input
Findings already in the orchestrator's context from the audit render. Each finding
carries: file_line, domain, severity, confidence, effort, symptom,
root_cause, reasoning_chain, counter_evidence_considered, suggested_fix.
Preamble — confirm runtime commands are on PATH
Confirm the plugin's runtime commands are reachable before any script call. If they are not on
PATH (e.g. the plugin is not installed or predates bin/), abort loudly.
command -v swe-workbench-clean-state-files >/dev/null 2>&1 || {
echo "swe-workbench runtime commands not on PATH — reinstall or update the swe-workbench plugin." >&2
exit 1
}
Phases
Phase 1 — Group by subsystem
For each finding derive a subsystem from file_line:
- Take the directory portion of the path (strip the filename).
- Use up to the first 2 path segments as the grouping key.
- Display label = last segment of that key:
src/auth/handler.ts→ keysrc/auth→ labelauthcommands/audit-codebase.md→ keycommands→ labelcommandsscripts/validate.py→ keyscripts→ labelscripts
- Root-level file (directory portion is empty, e.g.
README.md) → subsystemroot. - No path (tool-level or unknown finding) → subsystem
misc.
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.
- 2d ago First seen · 230 lines · 58 tokens per session scan A ede5267374a0
workflow-audit-emit-issues is a skill published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,273 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
diagnose
Structured debugging loop for exercise tests or build failures. Reproduce → isolate → hypothesize → fix → verify.
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…
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…