codegraph
Use when a project has a `.codegraph/` index and you need structural code intelligence — who calls a symbol, what breaks if you change it, where a symbol is defined, or how X reaches Y — instead of grep; also when enabling codegraph in a new project, or unsure which queries are MCP tools vs the codegraph CLI. Symptoms — about to grep for call sites, about to edit/rename/remove a symbol, picking up unfamiliar code, or a `codegraph_*` tool call failed with "not found".
What this skill does
# CodeGraph ## Overview codegraph is a tree-sitter AST knowledge graph (SQLite). Sub-millisecond queries return **structural** facts grep can't: call edges, impact sets, symbol definitions, flow paths — including dynamic-dispatch hops (callbacks, facades) grep silently misses. **Core rule:** for structural questions, query codegraph BEFORE grep. For literal text (string contents, comments, log messages) or once a file is already open, grep/Read is still right. ## Two entry points — neither is a superset `serve --mcp` exposes only *some* commands as `codegraph_*` MCP tools; the rest are Bash CLI only. (Verified on codegraph 0.9.7 — re-check with `codegraph --help` if a tool call fails.) | | MCP only | CLI only (`codegraph <cmd>`) | Both | |---|---|---|---| | | `trace`, `node`, `explore` | `callers`, `callees`, `impact`, `affected`, `status`, `files` | `search`/`query`, `context` | - **Navigate / understand** (want code bodies, trace X→Y, survey area) → MCP: `context` / `trace` / `node` / `explore` - **Analyze / list** (transitive impact, callers, affected tests) → CLI: `impact` / `callers` / `callees` / `affected` - **Overlapping `context` / `search` → default MCP** (output is LLM-tuned: no ANSI noise, self-budgets context, no shell round-trip). Use CLI only when already piping/grepping in a Bash flow. ## Proactive triggers — query before you act, not only when asked The structural question is usually implicit in an **action**, not a phrased question: - **Before edit / rename / remove a symbol** → `codegraph impact <symbol>` (transitive blast radius). The execution tool for the "trace the call chain before changing anything" review discipline; stronger than grep (catches dynamic dispatch). - **Before changing a method — who calls it?** → `codegraph callers <symbol>`, or MCP `codegraph_node <symbol>` (returns Called by ← call sites + Calls → callees, with file:line). Don't grep to count call sites. - **Picking up unfamiliar code** → MCP `codegraph_context "<task>"` first, then Read. - **Verify "how does X reach Y"** → MCP `codegraph_trace <from> <to>` (whole path, each hop's body, dynamic hops bridged). ## Reliability fallback - A capability isn't an MCP tool (impact/callers/callees)? → use the **Bash CLI**, do NOT fall back to grep. - A `codegraph_*` tool call fails / returns "not initialized" / the server disconnects? → **report it and retry / `codegraph init`**; don't silently grep — half a grep misses dynamic-dispatch call sites. - PHP DI / facade callee resolution is a known weak spot — only there, supplement with a grep second-check. ## New-project setup & known gotchas Read `reference.md` (in this skill dir) for: init steps, the `.mcp.json` snippet / `codegraph install`, the `.claude/settings.json` allowlist, and the gotchas (the tool-managed `CODEGRAPH_START/END` block gets overwritten on re-sync; that block's table over-promises CLI commands as `codegraph_*` MCP tools; `daemon.pid` isn't in the default gitignore).
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.