workflow-bug-triage

workflow-bug-triage is a skill for Claude Code, Codex from lugassawan/swe-workbench. It costs 65 tokens per session (2,482 once invoked), scanned A, original, MIT.

A bug-investigation workflow that finds the root cause and files a structured GitHub issue instead of changing the code immediately. The issue includes the affected code path and an assessment of the bug's impact.

In plain words
What is it for?
Use it to investigate unexpected behaviour, document the root cause, assess its impact, and create a GitHub issue for someone to act on.
Why use it?
It separates understanding a defect from fixing it, so an issue is not filed with a guessed cause or an unverified patch.

Skill for Claude CodeCodex

Part of the swe-workbench plugin — 60 skills, 25 commands, 32 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/lugassawan/swe-workbench/workflow-bug-triage
Any agent
npx skills add lugassawan/swe-workbench --skill workflow-bug-triage
Clone the repo
git clone --depth 1 https://github.com/lugassawan/swe-workbench

Made for: Claude Code, Codex.

Or install swe-workbench, the plugin that ships this one along with the rest of its 60 skills, 25 commands, 32 agents, 4 hooks.

Wrote 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.

agentmods badge for workflow-bug-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-bug-triage.svg)](https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-bug-triage)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02482
Opus 5 $0.00032 $0.01241
Sonnet 5 $0.00013 $0.00496
Haiku 4.5 $0.00006 $0.00248

Measured yesterday against content hash a52a26b951cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 yesterday.

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.

skills/workflow-bug-triage/SKILL.md · 181 lines

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:capture command directly.
  • The user is reviewing already-merged code for retroactive issues → use /swe-workbench:review first.

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.

Read the full file on GitHub · 181 lines

Files

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.

Changes

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.

  1. yesterday First seen · 181 lines · 65 tokens per session scan A a52a26b951cd

Subscribe to this mod's changes

workflow-bug-triage is a skill published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 2,482 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.

Related

Other skills, from other repositories

release

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…

hyhmrright/brooks-lint · 135 tokens

brooks-audit

Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…

hyhmrright/brooks-lint · 143 tokens

new-pattern

Guided workflow to create a new pattern following the project template and quality standards. Walks through topic validation, source verification, implementation, exercises, challenge questions, and bilingual docs.

Totoro-jam/battle-tested-patterns · 39 tokens

review

Perform a structured code review by composing validation checklists from relevant atoms based on what code changed. Loads atoms conditionally -- clean-code always, architecture/DDD/security/tests only when the delta touches their domain. Produces a severity-ordered report with specific locations and fixes. Use when…

techygarg/lattice · 95 tokens

skill-review

Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions…

techygarg/lattice · 180 tokens

context-anchoring

Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…

techygarg/lattice · 147 tokens