danieldekay/ai-ops/context-map

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Generate a map of all files relevant to a task before making changes using SymDex + LeanCTX call-graph and AST tools

Install

npx vskill@latest install danieldekay/ai-ops/context-map

SKILL.md

Context Map

Before implementing any changes, analyze the codebase and create a context map using efficient tools first.

Repo parameter: substitute <alias> below with your repository's SymDex index alias (e.g. the repo name). The MCP server prefix (mcp_symdex-mcp_*) may vary per harness — keep the tool family, adjust the prefix to what your environment exposes.

Mandatory Toolchain

DO NOT use raw read_file/grep_search for exploration. Use these in order:

Primary: SymDex (preferred)
StepToolPurpose
1mcp_symdex-mcp_build_context_pack(repo="<alias>", query="...")Broad evidence bundle — symbols, routes, tests, docs
2mcp_symdex-mcp_get_callers(repo="<alias>", name="symbol")Who calls this?
3mcp_symdex-mcp_get_callees(repo="<alias>", name="symbol")What does this call?
4mcp_symdex-mcp_get_file_outline(repo="<alias>", file="path")File structure without full read
5mcp_symdex-mcp_search_symbols(repo="<alias>", query="name")Find symbol by name
6mcp_symdex-mcp_semantic_search(repo="<alias>", query="intent")Find code by meaning
7mcp_symdex-mcp_search_routes(repo="<alias>", path_contains="/api/")Find HTTP endpoints
8mcp_symdex-mcp_get_repo_stats(repo="<alias>")Repo-level metrics
Alternative: LeanCTX (when SymDex unavailable or for AST-precise reads)
StepToolPurpose
1ctx_compose task="..."Ranked files with inline symbols — replaces 3-5 tool calls
2ctx_read mode=signaturesAll fn/class/type sigs via tree-sitter AST
3ctx_read mode=mapDeps + exports + API signatures (85-95% savings)
4ctx_callgraph action=callersWho calls this function (tree-sitter)
5ctx_callgraph action=calleesWhat this function calls (tree-sitter)
6ctx_search action=symbolAST-precise symbol lookup
7ctx_search action=semanticBM25 search by meaning
8ctx_graph action=relatedBFS blast radius from a file
9ctx_graph action=impactReverse dep analysis
10ctx_impactDeep change impact: trace dep chains + build graphs
11ctx_routesExtract HTTP routes from web frameworks
12ctx_overview task="..."Multi-resolution project map
Alternative: LeanCTX CLI (when MCP unavailable)
bash
lean-ctx read <file> -m signatures # AST signatures
lean-ctx read <file> -m map # deps + exports
lean-ctx grep <pattern> # compressed search
lean-ctx ls <dir> # compact tree
lean-ctx graph related <file> # blast radius
lean-ctx graph impact <file> # reverse deps
lean-ctx health # code health score

Fallback: If neither SymDex nor LeanCTX is available, use grep_search / read_file only for the specific files identified.

Task

{{task_description}}

Instructions

  1. Build context pack — build_context_pack(repo="<alias>", query="{{task_description}}") for broad evidence
  2. Trace call graph — For each primary symbol: get_callers + get_callees to find dependencies
  3. Get file outlines — get_file_outline for each affected file (not full reads)
  4. Find tests — search_symbols(query="test_<feature>") or search_text(query="def test_")
  5. Find patterns — semantic_search(query="similar pattern") for existing conventions
  6. Check index freshness — get_index_status(repo="<alias>") if stale, re-index with index_folder

Output Format

markdown
## Context Map
### Files to Modify
| File | Purpose | Changes Needed | Callers | Callees |
|------|---------|----------------|---------|---------|
| path/to/file | description | what changes | X calls it | it calls Y |
### Dependencies (may need updates)
| File | Relationship | Call Graph Evidence |
|------|--------------|---------------------|
| path/to/dep | imports X from modified file | `get_calees` → symbol |
### Test Files
| Test | Coverage | Found via |
|------|----------|-----------|
| path/to/test | tests affected functionality | `search_symbols` |
### Reference Patterns
| File | Pattern | Found via |
|------|---------|-----------|
| path/to/similar | example to follow | `semantic_search` |
### Risk Assessment
-[ ] Breaking changes to public API (check `get_callers` count)
-[ ] Database migrations needed
-[ ] Configuration changes required
-[ ] High caller count → high blast radius

Do not proceed with implementation until this map is reviewed.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/danieldekay/ai-ops/context-map/badge)](https://verified-skill.com/skills/danieldekay/ai-ops/context-map)

Something wrong with this skill or its page? Tell us.