explore
Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Defers to ODIN's Dispatch-First protocol (1/3/5 Explore-agent escalation). Trigger on "explore", "find where X is", "how does X work in the code", "map the codebase", "what files handle Y", or any architecture/pattern/tooling/dependency context request on a local repo — even without naming /explore.
What this skill does
# Explore Command Read-only codebase orientation. Emit architecture, pattern, tooling, and dependency summaries for a repo-local task. Do NOT write, edit, or commit files. ## When to Apply / NOT **Apply:** - Pre-implementation codebase orientation (feature, fix, refactor) - File and symbol mapping — "where is X defined", "what uses Y" - Architectural surveys — module boundaries, control flow, coupling - Dependency tracing — import graphs, transitive deps, config files **NOT apply:** - External library docs, SDK APIs, or framework behavior — use a doc-retrieval workflow instead - User wants a packed repo file as a deliverable artifact - Implementation, editing, or committing anything ## Process 1. **Scope** — parse the task. Identify files/dirs/concerns. State scope explicitly before dispatching. 2. **Dispatch decision** — for multi-file or uncertain tasks: dispatch Explore agent(s) instead of reading directly. Escalation: 1 agent for single-concern known scope; 3 agents for multiple concerns or unknown scope; 5 agents for cross-module or architectural survey. Auto-skip (direct reads allowed) only for single file under 50 LOC. 3. **Discovery** — token-efficient flags mandatory: - 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 -offset -limit` - Directory structure: `eza --tree --level=2` 4. **Synthesis** — emit all Required Output sections. No file writes. 5. **Heavy-codebase escape hatch** — scope > 50 files: use a codebase-packing tool if available as an internal analysis aid (not handed to the user as output); search the packed output for targeted extraction. ## Required Output Emit all 8 sections. Omit a section only when genuinely not applicable; state why. ### Task Understanding Brief restatement of the task and identified scope boundaries. ### Architecture Context ``` [Module/Layer Name] - path/to/file.ts:L10-50 — [Purpose] — [Relevance] - path/to/interface.ts — [Purpose] — [Relevance] ``` ### Pattern Context ``` [Pattern Category] - path/to/reference.ts — [Pattern description] — [How to apply] ``` ### Tooling Context ``` - Build: [command] — [when to run] - Test: [command] — [scope/coverage] - Lint: [command] — [config location] ``` ### Dependency Map ``` Internal: - module-a -> module-b (reason) External: - library-name@version — [usage context] ``` ### Critical Files Summary Prioritized list of files most relevant to the task: | Priority | File | Purpose | Action Hint | |----------|------|---------|-------------| | P0 | path/to/core.ts | Core logic | Modify | | P1 | path/to/types.ts | Type definitions | Extend | | P2 | path/to/utils.ts | Helpers | Reference | ### Constraints & Considerations - [Constraint 1]: [Impact on implementation] - [Constraint 2]: [Impact on implementation] ### Recommended Next Steps 1. [First action with specific file reference] 2. [Second action with specific file reference] ## 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`, any state-mutating bash command ## Anti-Patterns - Reading whole files when line ranges suffice — use `bat -r` or `Read -offset -limit` - Grepping/globbing before dispatching Explore agents on multi-file tasks — dispatch first - Bypassing token-efficient flags — `bat -P -p -n`, `rg -l`, `fd --max-results 50` - Re-entering a router or orchestrator skill from within this leaf skill — forbidden (recursion guard)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.