Arnie016/codex-prompt-templates / skills/codebase-graph-scout
codebase-graph-scout
UnverifiedUse graph-backed or semantic codebase intelligence before editing. Use when tasks need symbol search, blast radius, affected tests, architecture health, dependency paths, large-codebase context, Roam, CodeAlive, GraphRAG, or MCP code search. Skip for tiny scripts where rg/read is enough.
Codebase Graph Scout
Prefer graph tools when the repo is large enough that raw file reading will waste context.
Tool Preference
| Available tool | Use for |
|---|---|
roam-code | local symbol graph, preflight, impact, health, affected tests |
| CodeAlive MCP | hosted semantic/GraphRAG code search with API key |
rg + manifests | fallback for small repos or missing graph tools |
Roam Loop
roam init
roam health
roam understand
roam context <symbol>
roam preflight <symbol>
roam affected-tests <symbol>
Use --json for parsing and --budget <n> when context is tight.
CodeAlive Loop
- List data sources.
- Run
semantic_searchorgrep_search. - Fetch only the relevant artifacts.
- Expand relationships for the smallest useful set.
- Use chat/synthesis only after search results are insufficient.
Output
Return:
- symbols/files to read
- edit risk
- likely tests
- dependency or call paths that matter
- what not to touch
Reference source patterns in references/source-repos.md.
Validation
- The returned file/symbol set is smaller than a broad repo read.
- Claimed impact paths cite graph/search output or exact files.
- If graph tools are unavailable, the fallback
rg/manifest path is stated.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |