| name | explore |
| description | Answer an evidence question without touching production code — research external facts against primary sources, build or iterate a disposable prototype (its own bugfixes included), or baseline current repository behavior before deciding or implementing. Use when the question is answerable by reading, building, or measuring, with no user decision required; unsettled decisions belong to scout. Prototype iteration stays here, never implement. Prototypes are throwaway. |
explore
Answer an open question with evidence, without touching production code.
Three modes — pick whichever settles the question:
- research — documented or external facts: read source, docs, or the web;
record findings with links so claims stay traceable. Procedure:
../scout/references/research.md.
- prototype — an environment-specific behavior question that reading
cannot settle: build the smallest throwaway that answers it, outside
production paths. Prototypes are disposable; only a decision-encoding
fragment (a schema, a reducer, a type shape) may be inlined into
SPEC.md.
Fixing the prototype's own bugs is still this mode — "fix" routes to
implement only when the target is production code; iterate directly,
no re-routing pass per request. When the user approves porting, the port
is production work — route it by tier (spec → implement, or directly
under Light when small); the prototype never merges as-is. "Ship it
as-is" waives the rewrite, not the route — the port still earns its
tier's red tests and review. A prototype that is deployed or relied on
in real work is no longer throwaway: say so, and route its next change
by tier.
Procedure: ../scout/references/prototype.md.
- baseline — current repository behavior that must be preserved or
changed: capture it as runnable commands with observed output, so
verify
can compare later. Phrase each behavior the work must preserve as a guard —
"the system SHALL CONTINUE TO " — so preserved behavior
is a checkable claim, not an assumption.
Findings go where they will be used: decisions into SPEC.md, working
evidence into NOTES.md. If no bundle exists and the question feeds Full-tier
work, run spec first; otherwise deliver the findings in the conversation and
record anything worth keeping in the session task list — no bundle.
Exploration is read-only toward production code and never authorizes
implementation.
