Skip to content
Development
Skill

/explore

Use when asked to explore the codebase to map structure, symbols, and dependencies. Not for a single file under 50 LOC: read it directly.

From plugin
odin-claude-plugin
40200 skills

Claude Code

$ npx -y skills add OutlineDriven/odin-claude-plugin --skill explore --agent claude-code

SKILL.md

explore.SKILL.md
name: explore
description: 'Use when asked to explore the codebase to map structure, symbols, and dependencies. Not for a single file under 50 LOC: read it directly.'

Explore

Contract

| Field | Bound contract | |---|---| | Trigger | User says "explore", "find where X is", "how does X work in the code", or "map the codebase" for repo-local orientation. | | Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. | | Side effect | A structured orientation report in chat; may dispatch Explore subagents. No state mutation. | | Done | All 8 output sections emitted or applicability stated, scope declared, and dispatch/escalation rules followed. |

Inputs

  • Task text (supplied): the orientation question or concern to map.
  • Repo working tree (supplied by environment): read-only access to the local checkout.
  • Optional: specific files, directories, or concerns used to bound scope before dispatch.

Procedure

1. **Scope.** Parse the task; identify the files, directories, and concerns in scope. State the scope explicitly before any dispatch or read. Done when: the scope is stated explicitly before any dispatch or read. 2. **Dispatch decision.** For multi-file or uncertain tasks, dispatch Explore subagents instead of reading directly. Escalation: 1 subagent for a single-concern known scope; 3 subagents for multiple concerns or unknown scope; 5 subagents for a cross-module or architectural survey. Auto-skip (direct reads allowed) only for a single file under 50 LOC. Dispatch first; do not grep or glob a multi-file task before dispatching. Done when: the dispatch decision is made with the correct escalation tier, or direct reads are selected for a single file under 50 LOC. 3. **Discovery with token-efficient flags.** File discovery: `fd -e <ext> --max-results 50`. Symbol search: `ast-grep run -p 'PATTERN' -l <lang> -C 1` or `git --no-pager grep -n -C 2 'pattern'`. Content preview: `bat -P -p -n -r START:END file` or read with offset/limit. Directory structure: `eza --tree --level=2`. Done when: discovery is completed using token-efficient flags. 4. **Synthesis.** Emit all 8 output sections below. Omit a section only when genuinely not applicable and state why. Done when: all 8 output sections are emitted or omitted with a stated reason. 5. **Heavy-codebase escape hatch.** When scope exceeds 50 files, use a codebase-packing tool only as an internal analysis aid; never give packed output to the user. Search the packed output for targeted extraction. If no packing tool is available, narrow scope and state the narrowing. Done when: the heavy-codebase escape hatch is applied or scope is narrowed with a stated reason. 6. **Tool restrictions.** Allowed (read-only): `eza`, `fd`, `ast-grep` (find-only), `git grep`, `rg`, `bat`, `tokei`, `Read`, `codebase_search`, and any available codebase-analysis or codebase-packing MCP tooling. Banned: `Edit`, `Write`, `mcp__edit__edit_file`, `git commit`, and any state-mutating bash command. Done when: only allowed tools are used and no banned tool is invoked. 7. **Recursion guard.** Do not re-enter a router or orchestrator skill from within this leaf skill. Done when: no router or orchestrator skill is re-entered.

Failure and recovery

  • Scope too large (> 50 files). Apply the heavy-codebase escape hatch; if no packing tool is available, narrow scope, state the narrowing, and proceed with the reduced scope.
  • Empty or missing source. For each affected section, state that it does not apply and explain why rather than fabricating content.
  • Dispatch failure. Return a partial result containing the sections that could be filled; never claim the done predicate holds when required sections are missing.
  • Banned mutating tool attempted. Stop immediately, do not perform the mutation, and report the attempt. No rollback is needed because no mutation occurs.
  • Blocked / non-converged result. Terminal classification stating which sections could not be filled and the concrete reason.

Output

A structured orientation report with 8 sections in order: task understanding, architecture context, pattern context, tooling context, dependency map, critical files summary, constraints and considerations, and recommended next steps, omitting a section only when not applicable with a stated reason.

Read more
@outlinedriven
Ships withodin-claude-plugin

Formerly the ODIN Claude Plugin. The repository URL is unchanged. Outline-Driven Development, nicknamed ODIN, is a highly opinionated code-agent skill library: principles-first engineering, surgical editing, and workflow automation, published as installable

Stars on GitHub

Momentum

stars in total
40
Star history of OutlineDriven/odin-claude-plugin on GitHub, a chart by star-history.com

Other skills on odin-claude-plugin.

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills11d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about explore.

Which coding agents can use explore?
explore installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.