git-bisect-auto

git-bisect-auto is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 40 tokens per session (696 once invoked), scanned A, original, MIT.

An automated tool for using Git bisect, a process that searches a project's commit history to find when a bug first appeared. It runs a test command on selected commits and identifies the first failing one.

In plain words
What is it for?
Use it to find the commit that broke tests, compilation, or a specified file condition, then review the reported author, message, changed files, and diff summary.
Why use it?
It narrows a regression down without requiring you to inspect every commit between a working and broken version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/auto-bisect.sh --good v1.0 --bad HEAD --test "npm test".

Good fit Use it to find the commit that broke tests, compilation, or a specified file condition, then review the reported author, message, changed files, and diff summary.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex
agentmods
npx agentmods add skills/jansenanalytics/claudex/git-bisect-auto

Made for: Claude Code, Codex.

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 git-bisect-auto

README.md
[![agentmods](https://agentmods.dev/badge/skills/jansenanalytics/claudex/git-bisect-auto.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/git-bisect-auto)
Your own site
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/git-bisect-auto"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/git-bisect-auto.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 696 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00040 $0.00696
Opus 5 $0.00020 $0.00348
Sonnet 5 $0.00008 $0.00139
Haiku 4.5 $0.00004 $0.00070

Measured 3d ago against content hash 52e9462cad00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

git-bisect-auto 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.

skills/git-bisect-auto/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

git-bisect-auto

Automated git bisect to find the exact commit that introduced a bug. Run a test command against each bisect step, report the first bad commit with full context.

When to Use

  • A regression was introduced and you need to find which commit caused it
  • Narrowing down bug introductions in large commit ranges
  • Automating binary search through git history
  • Generating regression reports for issues/PRs

Scripts

auto-bisect.sh

Automated git bisect runner with safety features.

# Find which commit broke the tests
bash scripts/auto-bisect.sh --good v1.0 --bad HEAD --test "npm test"

# Find which commit introduced a file
bash scripts/auto-bisect.sh --good abc123 --bad def456 --test "test ! -f bug.txt"

# Find which commit broke compilation
bash scripts/auto-bisect.sh --good main~20 --bad main --test "make build"

Features:

  • Stashes uncommitted changes before starting, restores after
  • Runs git bisect start, sets good/bad, then git bisect run
  • After completion: shows first bad commit, author, date, message, diff stats, changed files
  • Cleans up bisect state even on failure

Test command convention: Exit 0 = good (no bug), exit non-zero = bad (bug present). Exit 125 = skip (untestable commit).

bisect-test-gen.sh

Generate ready-to-use test scripts for common bisect scenarios.

# Does it compile?
bash scripts/bisect-test-gen.sh --type compile --params "make build"

# Does a specific test pass?
bash scripts/bisect-test-gen.sh --type test --params "pytest tests/test_auth.py"

# Does the server start (and respond)?
bash scripts/bisect-test-gen.sh --type server --params "npm start,http://localhost:3000,5"

# Does a URL return 200?
bash scripts/bisect-test-gen.sh --type http --params "http://localhost:3000/api/health"

# Does output contain/not contain a string?
bash scripts/bisect-test-gen.sh --type grep --params "npm run build,error,invert"

Output: executable test script written to bisect-test.sh.

regression-report.sh

Read the full file on GitHub · 86 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. 3d ago First seen · 86 lines · 40 tokens per session scan A 52e9462cad00

Subscribe to this mod's changes

git-bisect-auto is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 696 once invoked, about $0.0002 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

advanced-git-rebase-bisect-worktree

Advanced git operations beyond add/commit/push. Use when rebasing, bisecting bugs, using worktrees for parallel development, recovering with reflog, managing subtrees/submodules, resolving merge conflicts, cherry-picking across branches, or working with monorepos.

rondoflow/rondoflow · 66 tokens

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.

sickn33/agentic-awesome-skills · 34 tokens

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

comet-github-issue-fix

A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.

rpamis/comet · 71 tokens

dev-fix

Unified developer workflow for fixing bugs. Analyzes issue-tracker context, cross-checks docs/code, proposes a solution, implements the fix, verifies locally, and delivers a PR/MR.

HoangNguyen0403/agent-skills-standard · 43 tokens