A bug-fixing workflow that assigns investigation and coding to separate sub-agents. It requires a failing reproduction test before changing the code and checks that the fix passes the full test suite.

Use it to investigate crashes, regressions, broken or unexpected behavior, write a failing test, implement a minimal fix, and prepare a hotfix branch and summary.

It helps distinguish the real cause of a behavioral problem from its symptoms and prevents weakening existing tests just to make them pass.

bug-fix — Skill for Claude Code and Codex by LuisFelipeMoro: A bug-fixing workflow that assigns investigation and coding to…

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/luisfelipemoro/harness-devkit/bug-fix

Any agent

npx skills add LuisFelipeMoro/Harness-devkit --skill bug-fix

Clone the repo

git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit

Made for: Claude Code, Codex.

Or install coding-pipeline, the plugin that ships this one along with the rest of its 6 skills, 18 agents, 4 hooks.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,115 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.

Model	Per session	Once invoked
Fable 5	$0.00075	$0.01115
Opus 5	$0.00037	$0.00558
Sonnet 5	$0.00015	$0.00223
Haiku 4.5	$0.00007	$0.00112

Measured 3d ago against content hash c35b40c213e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-fix 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 3d 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.

plugins/coding-pipeline/skills/bug-fix/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discipline: Failing reproduction test written RED before any fix. Never modify existing tests to fit the fix.

This is the one deliberate exception to the devkit's spec-first testing rule (feature work implements first, then writes and falsifies the specified tests — see CLAUDE.md). A bug fix keeps test-first because the RED run is the evidence that the root cause was actually found rather than guessed: a fix applied without a test that failed beforehand can just as easily be masking the symptom. The RED here is the falsification step, obtained for free.

Machine-checkable behavior contract: skill.spec.yml · dependency ledger: deps.toml (both generated by the skillspec CLI and git-ignored — Claude never loads them). Sub-agent dispatch prompts and report templates: references/dispatch.md.

Contract

Input: bug description + reproduction steps (ask if not provided).
Output: a minimal fix that turns a RED test GREEN, a green full suite, a Reviewer score, a Bug Fix Summary, and a PR from hotfix/{slug} to main.
Boundary: never weaken/delete/rewrite an existing test to make the fix pass; Reviewer sees changed files only.
Branching: a bug fix uses a hotfix branch cut from main — hotfix/{slug} — and nothing else. No delivery file, no release branch, no feature branches, no worktree: the fix commits straight onto the hotfix branch. The terminal step is a PR to main; never commit or merge to main directly. See ../../references/delivery-and-worktree.md.
Steps: 0) Cut hotfix/{slug} from main → 1) Investigate (Sam) → 2) Fix (Amelia) → 3) Verify (Quinn) → 4) Review → 5) Summary + PR to main.

Phase 1 — Investigate (Sam sub-agent)

Input: Bug description from user. Ask if not provided: "What's the wrong behavior? How do I reproduce it?" Output: BUG REPORT + SAM HANDOFF packet. Boundary: does NOT fix anything.

Dispatch Sam (model sonnet) using the Phase 1 template in references/dispatch.md. Show BUG REPORT and SAM HANDOFF to user before continuing.

Read the full file on GitHub · 69 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.

references/dispatch.md 2.4 KB

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.

3d ago First seen · 69 lines · 75 tokens per session scan A c35b40c213e5

Subscribe to this mod's changes

bug-fix is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,115 once invoked, about $0.0004 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 2026-08-31.

Debugging

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens