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-bug-triagegit 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-bug-triage)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-bug-triage"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-bug-triage/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-bug-triage"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-bug-triage.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 | $0.00065 | $0.02482 |
| Opus 5.5 | $0.00026 | $0.00993 |
| Sonnet 5.5 | $0.00013 | $0.00496 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
workflow-bug-triage 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 1mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Bug Triage (investigate + file issue)
Announce at start: "I'm using the workflow-bug-triage skill to investigate the root cause and file a GitHub issue."
When to invoke
- The user describes a bug, defect, or unexpected behaviour and wants it documented (not fixed in-session).
- Phrases: "investigate this bug", "find the root cause", "file an issue for this bug", "triage this".
- The bug is in code the user does not own, or fix-planning needs to happen separately.
- The investigation needs to produce a shareable artifact (an issue) other people will act on.
When NOT to invoke
- The user wants a fix now → use
/swe-workbench:debug(counterpart skill that ends in code change + regression test). - The root cause is already known and only the fix is needed → use
/swe-workbench:debug. - The user is capturing a feature request, idea, or improvement (not a bug) → use the
/swe-workbench:capturecommand directly. - The user is reviewing already-merged code for retroactive issues → use
/swe-workbench:reviewfirst.
Iron Law
NO FIXES WITHOUT ROOT CAUSE FIRST.
If the user proposes a fix before the root cause is established, refuse politely:
"I'd like to find the root cause before suggesting a fix — otherwise we risk piling band-aids on a deeper issue. Can I run the investigation first?"
Red flags that mean STOP investigating-by-fixing and return to Phase 1:
- "Quick fix for now…"
- "Just try changing X…"
- "It's probably X, let me patch it."
- "Let me just patch this and move on."
- "Looks like a typo, just fix it."
- "We can fix it later, just suppress the warning."
A symptom is not a cause. A patch that hides a symptom is a regression hiding behind a green test.
Composition
For the inner investigation loop (read-before-guessing, reproduce-before-theorizing, falsify-before-fixing), defer to superpowers:systematic-debugging via the Skill tool — same delegation pattern as agents/debugger.md.
If superpowers:systematic-debugging is unavailable, run the same loop inline — never skip it.
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.
- 1mo ago First seen · 181 lines · 65 tokens per session scan A a52a26b951cd
workflow-bug-triage is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 2,482 once invoked, about $0.0003 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…