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/ryanb/dotfiles/bisectnpx skills add ryanb/dotfiles --skill bisectgit clone --depth 1 https://github.com/ryanb/dotfilesWhat 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 | $0.00018 | $0.00614 |
| Opus 5 | $0.00009 | $0.00307 |
| Sonnet 5 | $0.00004 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
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 yesterday.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bisect — Find the First Bad Commit
Use git bisect to binary-search through commit history and find the first commit that introduced a failure.
Step 1: Ensure clean working tree
Check that there are no staged or unstaged changes. If there are, stop and tell the user they need a clean working tree before bisecting, since git bisect checks out older commits.
git status --porcelain
If the output is non-empty, stop and ask the user to commit or stash their changes first.
Step 2: Determine the test command
Use $ARGUMENTS to understand what the user wants to test. This should describe a command or check that fails on the current commit. Determine the exact shell command to run.
Step 3: Verify the current commit is bad
Run the test command on the current commit (HEAD). If it passes (exits 0), stop and tell the user — the current commit doesn't exhibit the failure, so there's nothing to bisect.
Step 4: Find a good commit
Start searching backwards from HEAD in steps of 10 commits to find a commit where the test passes.
git stash --include-untracked -q 2>/dev/null; true
git checkout HEAD~10 --quiet
Run the test command. If it still fails, go back another 10 commits (HEAD~10 from the current position). Repeat until either:
- A passing commit is found, or
- You've gone back 100+ commits without finding a passing one — stop and ask the user for guidance (maybe a known-good commit SHA).
Once a good commit is found, note its SHA.
Step 5: Run git bisect
Return to the original branch first, then start bisecting:
git checkout - --quiet
git bisect start
git bisect bad
git bisect good <good-commit-sha>
Git will check out a middle commit. Run the test command on it:
- If the test fails →
git bisect bad - If the test passes →
git bisect good
Repeat until git reports the first bad commit.
Step 6: Record the result and clean up
Save the first bad commit SHA and message. Then reset:
git bisect reset
What ships with it
1 file 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.
- yesterday First seen · 78 lines · 18 tokens per session scan A 294f7646c92e
bisect is a skill published in the GitHub repository ryanb/dotfiles (2,399 stars, last pushed 12d ago), licensed MIT. It adds 18 tokens to every session and 614 once invoked, about $0.0001 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…