git:bisect

git:bisect is a command for Claude Code from geoffjay/claude-plugins. It costs 19 tokens per session (2,850 once invoked), scanned A, original, MIT.

A guided Git workflow that uses binary search to find the commit that introduced a bug. You mark commits as good or bad while Git tests the middle of the history.

In plain words
What is it for?
Use it to investigate when a regression began, with checks for uncommitted changes and an interactive good-or-bad testing process.
Why use it?
Checking every commit one by one is slow when a bug could have been introduced anywhere in a long history.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: positional $N argument.

Good fit Use it to investigate when a regression began, with checks for uncommitted changes and an interactive good-or-bad testing process.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/geoffjay/claude-plugins/bisect
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.

Clone the repo
git clone --depth 1 https://github.com/geoffjay/claude-plugins

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/geoffjay/claude-plugins/bisect/github.svg)](https://agentmods.dev/commands/geoffjay/claude-plugins/bisect)
Your own site
<a href="https://agentmods.dev/commands/geoffjay/claude-plugins/bisect"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/bisect/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.

agentmods 80×15 button for git:bisect

Your own site · 80×15
<a href="https://agentmods.dev/commands/geoffjay/claude-plugins/bisect"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/bisect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,850 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 $0.00019 $0.02850
Opus 5.5 $0.00008 $0.01140
Sonnet 5.5 $0.00004 $0.00570
Haiku 4.5 $0.00002 $0.00285

Measured 1mo ago against content hash 5fe3b6968baf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git:bisect 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.

plugins/utilities/git/commands/bisect.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Bisect - Binary Search for Bug-Introducing Commits

Interactive git bisect workflow to find commits that introduced bugs using binary search.

Command

/git:bisect [mode] [commit-ref]

Arguments

  • $1: mode - start|good|bad|skip|reset (optional, interactive if not provided)
  • $2: commit-ref (optional, depends on mode)

Description

Git bisect uses binary search to efficiently find the commit that introduced a bug. Instead of checking every commit, it splits the commit range in half repeatedly, asking you to test each midpoint. This can find a bug in log(n) checks instead of n checks.

Workflow

Starting a Bisect Session

  1. Pre-flight checks:

    • Check if bisect is already in progress: git bisect log
    • Check for uncommitted changes: git status --porcelain
    • If changes exist, warn user and suggest stashing
  2. Gather information:

    • Ask for the "good" commit (where bug didn't exist)
      • Default: last tag or commit from 1 week ago
      • User can specify: commit hash, tag, branch name
    • Ask for the "bad" commit (where bug exists)
      • Default: HEAD (current commit)
      • User can specify: commit hash, tag, branch name
    • Calculate and show number of commits between good and bad
    • Estimate number of steps needed: ~log2(n)
  3. Start bisect:

    git bisect start
    git bisect bad [bad-commit]
    git bisect good [good-commit]
    
  4. Show first commit to test:

    • Display commit hash, date, author, message
    • Show which files changed: git show --stat <commit>
    • Provide clear instructions on what to test

During Bisect Session

  1. Test current commit:

    • Ask user to test whether the bug exists
    • Provide clear instructions:
      • "Run your tests"
      • "Manually test the feature"
      • "Check the logs"
    • Wait for user feedback
  2. Mark commit based on test result:

    • If bug exists: git bisect bad
    • If bug doesn't exist: git bisect good
    • If commit is untestable (won't build, etc): git bisect skip
    • Option to abort: git bisect reset

Read the full file on GitHub · 422 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. 1mo ago First seen · 422 lines · 19 tokens per session scan A 5fe3b6968baf

Subscribe to this mod's changes

git:bisect is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 11mo ago), licensed MIT. It adds 19 tokens to every session and 2,850 once invoked, about $0.0001 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.