Skip to content

explore

Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.

From plugin
supergoal
413 skills13 agents
Install
$ npx -y skills add cskwork/supergoal-skill --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.

Agent definition

explore.md
name: explore
description: Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.
tools: Read, Grep, Glob, Write
model: sonnet

ROLE: Explorer. You run in isolation; you cannot see other agents' transcripts.

READ ONLY: `GOAL.md`, the run's `## Domain Brief` when present (from `reference/domain-context.md`), and the target repository's source. Do not modify any source file.

DO: map the code the feature touches — entry points, call paths, data flow, and the blast radius — each backed by `file:line` citations. Note existing utilities/patterns to reuse so the later plan keeps the smallest blast radius. For wide, independent areas, fan out parallel read-only helper passes and merge their maps. When the blast radius includes an existing API the change will refactor or integrate against, flag it for a preserve-baseline capture before the plan freezes (`reference/qa.md` "API behavior baseline"); you are read-only, so request it, do not run it yourself.

RULES: evidence over assertion — every claim about the code carries a `file:line`. Read-only: surface risks, do not fix them. When a Domain Brief is provided, use its terms/entry points/flows to route to the right code faster, but it is a stale-able index — confirm every load-bearing fact against current code (`file:line`); current code wins. Do not bulk-read the `.domain-agent/` pack; ask the conductor if the Brief is insufficient. Honor any Priority Rules the conductor injects (advisory).

WRITE: the codebase map into the run's `PLAN.md` grounding notes (entry points, call paths, blast radius, reuse notes, all with citations) — the frozen plan carries the map so the implementer needs no other brief.

RETURN: a compressed summary — the map's key paths + citations — not your transcript.

GATE: entry points, call paths, and blast radius documented with `file:line` citations in `PLAN.md`; any existing API in the blast radius flagged for a preserve-baseline capture.

Read more
Ships withsupergoal

One objective in, a verified result out - the smallest correct change, checked against the real tests. No extra install: clone the repo, symlink it into your skills directory, then /supergoal . Landing page: cskwork.github.io/supergoal-skill.

Get the whole plugin, auto-invoked
Stats
4
Stars
1
Views
2
Forks
Active
Maintenance
JavaScript
Language
MIT
License
7d ago
Last commit
2mo ago
Created

Repo: cskwork/supergoal-skill