| name | explore |
| description | Understand the code and the solution space: trace real flows, compare genuinely different approaches, and choose a direction. Runs only on an explicit CoderKit explore request. |
Explicit activation
Run this workflow only when the user explicitly requests CoderKit and names this tool. Do not suggest, infer, or auto-select it from task context. If it was selected without an explicit request, continue with normal host behavior without applying or mentioning CoderKit.
Prompting envelope
Structure the work in this order:
- Outcome: state the result the user wants before choosing an approach.
- Relevant context: gather what the prompt, repository, and named artifacts already provide before asking for anything.
- Important boundaries: identify the scope, authority, and constraints the work must not cross.
- Work: execute against the outcome within those boundaries.
- Verification: prove the outcome with the completion evidence this tool requires.
Ask only when missing information materially changes the result or required authority. Accept steering without restarting the workflow.
Proportionality
Right-size the workflow to the task. Use a fast path when the outcome and evidence are obvious; use deeper investigation only when uncertainty, risk, or scope warrants it. Do not create documents, dispatch agents, add process infrastructure, or expand test coverage merely because the workflow can — the work artifacts below are the one exception: they are mandated completion evidence, not discretionary documents. Stop when the completion evidence is satisfied. A finished, verified result is better than a perfect process.
Treat user-named files, URLs, tools, and prior artifacts as authoritative inputs: inspect them before substituting a generic alternative. Keep tangential cleanup and speculative improvements out of the active scope unless the user asks for them.
Work artifacts
Persistent work products live in the target project under docs/work/NNN-short-name/: NNN is a zero-padded index allocated as the highest existing index plus one (starting at 000), and short-name is a kebab-case name derived from the request.
plan.md — written by plan whenever it runs; the stable contract later tools read as authority.tasks.md — created and maintained by implement from the plan's units: main tasks, subtasks, and any subagent or orchestration assignments, with statuses updated as work progresses.tasks/ — optional subfolder, created only when a single task needs a dedicated brief (for example a subagent fan-out).
Explore produces no artifact. Tools other than plan and implement read these files but do not create them.
Completion
Finish with the evidence required by this tool, then name the natural next step — the next CoderKit tool in the workflow when one applies (explore → plan → implement → verify → commit, with debug for unexpected behavior), or nothing when the work is complete. Offer it as a suggestion the user can invoke; never invoke another CoderKit tool yourself, and never start the suggested work. This applies only at the end of an explicitly requested workflow: outside one, do not suggest CoderKit tools at all.
Explore
Method
- Scope what the exploration must answer: the outcome the user wants and the decision it feeds. Separate the outcome from any proposed implementation.
- Read repository instructions, project documentation, and user-named artifacts before implementation files. Ground everything in the actual subject, never in generic advice detached from it.
- Trace the real flows end to end: entry points, callers, control and data paths, configuration, and external boundaries. Map the patterns, conventions, and utilities later work should reuse.
- When the direction is open, generate genuinely different candidates before evaluating them. When the subject is broad, decompose it into a few non-overlapping surfaces derived from the evidence; skip both for a factual lookup.
- Critique every candidate against the outcome, constraints, leverage, complexity, and risks. Reject weak or redundant candidates explicitly and briefly.
- Present only the strongest two or three survivors with their meaningful trade-offs. Recommend one and explain the decisive reason.
- Stay strictly read-only: no edits, no working-tree mutations, no dependency installs, no speculative fixes.
- Stop when the question is answered or a direction can be chosen. Report remaining unknowns as unknowns instead of papering over them with plausible guesses.
Guardrails
- Repository evidence beats generic best practice; verify a claim by reading the code that implements it.
- More ideas are useful only when followed by real filtering.
- Findings and direction are a report, not a mandate: do not slide into requirements, planning, or implementation.
Completion evidence
Key files, traced flows, chosen direction or answer with trade-offs, and open unknowns.
