bisect

A workflow for using Git bisect to find the first commit that introduced a regression. A regression is a behavior, test, or build that worked before and now fails.

In plain words
What is it for?
Use it to investigate a reproducible regression by supplying a known-good version, a known-bad version, and a command that tests the behavior.
Why use it?
It narrows a long sequence of changes to the commit where the problem first appeared, provided there is a reliable test that distinguishes working from broken code.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/paultyng/skill-issue/bisect
Any agent
npx skills add paultyng/skill-issue --skill bisect
Clone the repo
git clone --depth 1 https://github.com/paultyng/skill-issue

Made for: Claude Code, Codex.

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00121 $0.02248
Opus 5 $0.00060 $0.01124
Sonnet 5 $0.00024 $0.00450
Haiku 4.5 $0.00012 $0.00225

Measured 2d ago against content hash a81227e67424, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bisect scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

go run ./cmd/server & PID=$!; sleep 1; curl -fsS localhost:8080/health; kill $PID
skills/bisect/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bisect

Drive git bisect to isolate the first commit that introduced a bug, then report it. The skill stops at the report. Fixing belongs to the user with full context.

When to use

  • User asks to "bisect", "find the commit that broke X", says "this used to work", or names a regression in a specific test/build target.
  • ci-debug-loop exhausted log analysis without identifying a clear cause.
  • A behavior, test, or build that was green at a known earlier point is now red.

Do not use when the bug is obviously in the most recent commit (inspect it), or when the reproducer is too fragile/flaky to drive an automated bisect (fix the flake first).

Inputs (confirm before starting)

Per confirm-before-implementing, gather these before touching git bisect:

  • Symptom: one-line description of what's broken (e.g. "TestExchangeToken fails with unauthorized").
  • Reproducer: a shell command that exits 0 when the bug is absent, 1 when present. If the user can't supply one, build it together (see Reproducer strategy).
  • Known-bad ref: default HEAD.
  • Known-good ref: default oldest commit within the last 2 weeks:
    git rev-list --since='2 weeks ago' --reverse HEAD | head -1
    
    If the user has a tag, branch, or specific date in mind, use it instead.

Reproducer strategy

The reproducer must work at every commit in the bisect range. The reproducer that exists today often won't: APIs change, test files don't yet exist on old commits, etc. Pick the highest-applicable strategy:

  1. External reproducer (preferred). A self-contained shell script in $TMPDIR (e.g. /tmp/repro.sh) that builds and exercises the project from outside the source tree. Hits a stable surface (CLI flag, HTTP endpoint, exported function with stable signature) that survived the bisect range. Examples:
    # CLI: build and check observable behavior
    go build -o /tmp/foo ./cmd/foo && /tmp/foo --some-flag | grep -q expected
    # HTTP: spin up server, hit endpoint, kill
    go run ./cmd/server & PID=$!; sleep 1; curl -fsS localhost:8080/health; kill $PID
    
    This survives any in-tree changes because the reproducer doesn't live in the tree.

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 121 tokens per session scan A a81227e67424

Subscribe to this mod's changes

bisect is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 22d ago), licensed MIT. It adds 121 tokens to every session and 2,248 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

promptscript

PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files. Use when working with PromptScript syntax, creating or editing .prs files, adding blocks like @identity, @standards, @restrictions, @shortcuts, @skills, or @agents, configuring promptscript.yaml, resolving compilation errors…

mrwogu/promptscript · 135 tokens

thesis-control

Use when AI-assisted thesis edits risk claim drift, scope creep, loss of author control, or repeated revisions that fail to converge; provides spine cards, edit contracts, drift audits, revision escalation, and human gates.

yha9806/academic-writing-toolkit · 47 tokens

helius-jupiter

Skill "helius-jupiter" from helius-labs/core-ai, covering helius x jupiter — build defi apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. jupiter api key.

helius-labs/core-ai · 0 tokens

argument-governance

Build and audit the manuscript argument system: intent, gap-contribution alignment, hierarchical claims, evidence balance, limitations, and reviewer attack surfaces. Use when a paper, thesis chapter, review article, or rebuttal needs explicit intent registers, contribution chains, claim hierarchy, argument maps…

yha9806/academic-writing-toolkit · 81 tokens

verify

Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.

yha9806/academic-writing-toolkit · 26 tokens

map

Show or update the mapping between literature and thesis chapters — which sources support which arguments. Use for tracking coverage.

yha9806/academic-writing-toolkit · 24 tokens