Bisect Regression

Core Question

Which commit introduced a regression, and what evidence supports that conclusion?

When To Use

Use this skill when:

• the user has a known good and known bad commit or range
• a reproducible test command can identify pass/fail
• the user asks to bisect a regression
• manual or automated bisect is appropriate

When Not To Use

Do not use this skill when:

• debugging without a reproducible signal
• fixing the regression after identification
• running bisect on dirty user work
• rewriting history or pushing results

Route to:

• dirty current work routes to worktree-management, stash-shelve, or atomic-commits
• conflicts during checkout route to undo-recover or stop
• root-cause fix routes to coding workflow outside this library

Required Evidence

Before action, inspect or establish:

• known bad commit or current bad state
• known good commit
• test command and expected signal
• clean or isolated worktree state
• flakiness indicators
• generated files or build artifacts that may change during test

No-evidence rule:

• Do not make strong claims without observed evidence.
• State assumptions when proceeding under incomplete evidence.
• Stop when missing evidence affects safety, correctness, user work, remote state, or irreversible action.

Operating Contract

You MAY:

• inspect relevant repository state and project files.
• generate a plan, report, or local artifact within the declared risk scope.
• route to another skill when the requested action is outside this skill's owner boundary.

You MUST:

• inspect before acting.
• keep the task within the declared owner boundary.
• classify state and risk before any meaningful action.
• preserve unrelated user work.
• verify outcomes proportional to risk.
• report evidence, assumptions, actions, verification, and residual risk.

You MUST NOT:

• invent project policy.
• expose secrets or sensitive values.
• mutate unrelated files or refs.
• perform destructive, remote, shared, history-rewriting, or irreversible actions without explicit action-specific confirmation.
• continue after unexpected destructive output.

State / Risk Table

Workflow

1. Identify the user goal and current owner boundary.
2. Inspect required evidence.
3. Classify repository/task state.
4. Classify risk using the declared scope.
5. Choose the minimal sufficient action or route.
6. Execute only allowed actions, if any.
7. Verify outcome or self-check the artifact.
8. Report result, evidence, verification, assumptions, and residual risk.

Decision Rules

• Require clean or isolated worktree before checkout-based bisect.
• Always reset bisect state at the end or on stop.
• Do not claim root cause from one flaky run.
• Verify candidate with neighbor checks when feasible.

Tool Rules

• May inspect logs, ranges, and status.
• May run bisect only after explicit plan and confirmation.
• Must not push or rewrite history.
• Must not leave repository in bisect state.

Verification

Minimum verification:

• Verify bisect reset occurred.
• Verify candidate commit with repeated or neighbor checks when feasible.
• Report test command and confidence.

Risk-based floor:

• R0-R1: evidence inspected and output self-checked.
• R2: inspect resulting diff or local state.
• R3: verify local state and report recovery limits.
• R4-R5: require explicit confirmation, preflight evidence, and post-action verification where this skill owns the action.

Output Contract

Final response must include:

## Result

- Decision, action, or artifact produced.

## Evidence

- Files, commands, diffs, refs, or assumptions used.

## Verification

- Checks performed and their result.

## Risks / Limitations

- Remaining uncertainty, blocked actions, or routed next steps.

Stop / Confirmation Rules

Stop when the repository state is dirty, conflicted, diverged, missing required evidence, or ambiguous in a way that could overwrite user work, invalidate the requested scope, or require a gated action.

Require explicit action-specific confirmation for:

• destructive local mutation.
• remote/shared mutation.
• history rewriting.
• security/secret/data impact.
• irreversible or hard-to-recover operation.

Broad approval such as "do whatever" is not enough for R4-R5 actions.

Lazy-load References

Load references/bisect-workflow.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.

Load references/flaky-tests.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.

Load references/worktree-isolation.md when:

• the task needs the detailed guidance described by the file name.
• the state/risk table identifies an ambiguous or high-risk path.