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.
npx agentmods add skills/sjungling/sjungling-claude-plugins/git-bisect-debuggingnpx skills add sjungling/sjungling-claude-plugins --skill git-bisect-debugginggit clone --depth 1 https://github.com/sjungling/sjungling-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/skills/sjungling/sjungling-claude-plugins/git-bisect-debugging)<a href="https://agentmods.dev/skills/sjungling/sjungling-claude-plugins/git-bisect-debugging"><img src="https://agentmods.dev/badge/skills/sjungling/sjungling-claude-plugins/git-bisect-debugging.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01656 |
| Opus 5 | $0.00047 | $0.00828 |
| Sonnet 5 | $0.00019 | $0.00331 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
git-bisect-debugging 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 5d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Bisect Debugging
Overview
Systematically identify which commit introduced a bug or regression using git bisect. Binary search through commit history to find the exact commit that introduced the issue. Main agent orchestrates, subagents execute verification at each step.
Announce at start: "I'm using git-bisect-debugging to find which commit introduced this issue."
Quick Reference
| Phase | Key Activities | Output |
|---|---|---|
| 1. Setup & Verification | Identify good/bad commits, verify clean state | Confirmed commit range |
| 2. Strategy Selection | Choose automated/manual/hybrid approach | Test script or verification steps |
| 3. Execution | Run bisect with subagents | First bad commit hash |
| 4. Analysis & Handoff | Show commit details, analyze root cause | Root cause understanding |
Limitations (By Design)
This skill focuses on straightforward scenarios. It does NOT handle:
- Complex merge commit issues (would need
--first-parent) - Flaky/intermittent test failures (would need statistical approaches)
- Build system failures across many commits (would need advanced skip strategies)
For these scenarios, manual git bisect with user guidance is recommended.
Critical Rules
These are non-negotiable. No exceptions for time pressure, production incidents, or "simple" cases:
- ANNOUNCE skill usage at start
- CREATE TodoWrite checklist immediately (copy from "The Process" below)
- VERIFY safety checks in Phase 1 -- working directory must be clean, good commit must be verified good, bad commit must be verified bad. If any check fails, abort and fix before proceeding.
- USE AskUserQuestion for strategy selection in Phase 2 -- present all 3 approaches, do not default to automated without asking
- LAUNCH subagents for verification in Phase 3 -- never run verification in main context; each commit tested in isolated subagent via Task tool
- HANDOFF to systematic-debugging in Phase 4 -- after finding the bad commit, investigate root cause, not just what changed
What ships with it
3 files 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.
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.
- 5d ago First seen · 164 lines · 94 tokens per session scan A 45b62f161dca
git-bisect-debugging is a skill published in the GitHub repository sjungling/sjungling-claude-plugins (13 stars, last pushed 21d ago), licensed MIT. It adds 94 tokens to every session and 1,656 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.
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…