bisect

A binary-search method for finding the source of a bug or regression. It repeatedly tests the midpoint of a defined range, such as commits, settings, dependency versions, or code modules, to narrow the cause.

In plain words
What is it for?
Use it when you have a clear symptom and a known search range. It can investigate Git history, configuration choices, dependency versions, or code areas.
Why use it?
Checking every possible cause can take a long time. Halving the search space after each pass or failure isolates the likely source with fewer tests.

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

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,563 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.01563
Opus 5 $0.00000 $0.00781
Sonnet 5 $0.00000 $0.00313
Haiku 4.5 $0.00000 $0.00156

Measured 2d ago against content hash 8d2c030a25fc, 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 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 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.

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.

skills/bisect/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binary search for root cause. Defines a search space and pass/fail oracle, then iteratively tests midpoints — halving the space each step until the root cause is isolated. Works across git history, configuration, dependencies, or code modules.

Arguments

$ARGUMENTS — format: "description of the bug or regression" with optional flags

Parse Arguments

Extract:

  • bug_description: the quoted or unquoted description of the symptom or regression

If the bug description is missing or unclear, ask the user to clarify before proceeding.

Phase 1: Define the Search Space

Work with the user to establish four things before starting the search loop.

1. The symptom — what is broken? What does failure look like? Get a concrete, observable description (error message, wrong output, crash, performance degradation).

2. The search dimension — where to search. Determine which applies:

  • Git history: a known-good commit and a known-bad commit (classic git bisect)
  • Configuration space: a set of config keys that might cause the issue
  • Dependency versions: which dependency upgrade broke things
  • Code modules: which module is responsible for the regression

3. The test oracle — how to determine pass/fail at each midpoint:

  • A specific test command (npm test, pytest tests/foo.py, go test ./..., etc.)
  • A behavior check (does endpoint X return 200? does the build succeed?)
  • A manual check (agent reads code or output and assesses)

4. Known bounds — the "good" end and "bad" end of the search space.

For git history bisect, run:

git log --oneline <good_commit>..<bad_commit>

to enumerate the search space. Count the candidates and report: "Search space: N commits. Expected steps: ceil(log2(N))."

For configuration bisect, list all changed config keys between the working and broken state. For dependency bisect, list all upgraded packages with old and new versions sorted by update date.

Present the search space summary to the user and confirm before proceeding. Adjust if the user gives feedback.

Read the full file on GitHub · 156 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 · 156 lines · 0 tokens per session scan A 8d2c030a25fc

Subscribe to this mod's changes

bisect is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,563 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

speckit.specify

Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.

caipe-io/ai-platform-engineering · 0 tokens

speckit.clarify

Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.

caipe-io/ai-platform-engineering · 0 tokens

local-integration-testing

Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.

caipe-io/ai-platform-engineering · 44 tokens

release-docs

Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…

caipe-io/ai-platform-engineering · 76 tokens

update-docs

Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…

caipe-io/ai-platform-engineering · 70 tokens

docker-compose-first-install

Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.

caipe-io/ai-platform-engineering · 60 tokens