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.
git clone --depth 1 https://github.com/geoffjay/claude-pluginsWrote 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.
[](https://agentmods.dev/commands/geoffjay/claude-plugins/bisect)<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.
<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>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 5.1 | $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 |
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.
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
-
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
- Check if bisect is already in progress:
-
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)
- Ask for the "good" commit (where bug didn't exist)
-
Start bisect:
git bisect start git bisect bad [bad-commit] git bisect good [good-commit] -
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
-
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
-
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
- If bug exists:
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.
- 1mo ago First seen · 422 lines · 19 tokens per session scan A 5fe3b6968baf
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.
Other commands, from other repositories
barista-fix
Attempt a small, focused fix for a frappe-ui issue and open a draft PR.
fix-issue
Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to…
unbloat
Remove dead code, duplicate files, and unused dependencies with user approval at each step. Backs up before deleting.
payload-revert
Stage reverts for high-confidence payload candidates identified by payload-analysis.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.
fix-issue
Analyze and fix the GitHub issue: $ARGUMENTS.