bisect-debug

bisect-debug is a skill for Claude Code, Codex from paulinevos/claude-stuff. It costs 88 tokens per session (652 once invoked), scanned A, original, MIT.

A debugging workflow that uses `git bisect` to find the commit where a regression began. A regression is a feature that used to work but later stopped working.

In plain words
What is it for?
It is for creating or reusing a pass/fail check, locating a known-good commit, running an automated bisect, and then fixing the identified regression.
Why use it?
It replaces guesswork with a binary search through the project’s history, narrowing the cause to a specific change.

Skill for Claude CodeCodex

Part of the git-workflow plugin — 4 skills 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/paulinevos/claude-stuff/bisect-debug
Any agent
npx skills add paulinevos/claude-stuff --skill bisect-debug
Clone the repo
git clone --depth 1 https://github.com/paulinevos/claude-stuff

Made for: Claude Code, Codex.

Or install git-workflow, the plugin that ships this one along with the rest of its 4 skills.

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 bisect-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulinevos/claude-stuff/bisect-debug.svg)](https://agentmods.dev/skills/paulinevos/claude-stuff/bisect-debug)
Your own site
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/bisect-debug"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/bisect-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 652 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 $0.00088 $0.00652
Opus 5 $0.00044 $0.00326
Sonnet 5 $0.00018 $0.00130
Haiku 4.5 $0.00009 $0.00065

Measured 4d ago against content hash 75b5b351fe3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bisect-debug 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 4d 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/git-workflow/skills/bisect-debug/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bisect-debug

A regression means there's a specific commit where behavior flipped from good to bad. Bisect finds it in O(log n) steps by binary-searching history with a pass/fail test. The payoff is a precise culprit commit you can read and fix, instead of guessing.

Steps

  1. Turn the bug into a pass/fail command.
    • If an existing test already covers it, use that — it should fail at HEAD.
    • Otherwise write a throwaway check outside the repo, e.g. /tmp/bisect-check.sh, that reproduces the bug and exits 0 when the behavior is good and non-zero when it's bad. Keeping it outside the working tree is the trick: it stays put across every checkout, so you never add it to the repo or shuffle a test commit through history. git bisect run executes it from the repo root, so reference repo files by their normal paths (and include a build step if the project needs one).
  2. Find a known-good commit. Check out older commits and run the command until it passes; note that commit as [good-commit].
  3. Run the bisect automatically:
    git bisect start HEAD [good-commit]
    git bisect run bash /tmp/bisect-check.sh   # or the existing test command
    
    Git checks out midpoints and runs the command at each until it reports [bad-commit] is the first bad commit. Finish with git bisect reset to return to where you started.
  4. Analyze the culprit. git show [bad-commit] — explain what in it caused the regression.
  5. Fix it properly. Suggest a new bug-fix commit that resolves the bug and adds a proper regression test committed into the repo, so the behavior is protected going forward (the throwaway /tmp script was only scaffolding — discard it). Always a fresh commit, never a rewrite of the culprit — it is almost always already on shared history, which must not be rewritten (others may have built on it). Write the fix commit with an imperative subject line and a body explaining why the bug occurred, not how the diff works.

Read the full file on GitHub · 49 lines

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. 4d ago First seen · 49 lines · 88 tokens per session scan A 75b5b351fe3a

Subscribe to this mod's changes

bisect-debug is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 22d ago), licensed MIT. It adds 88 tokens to every session and 652 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 2026-08-30.

Related

Other skills, from other repositories

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