borda/ai-rig/scan-codebase

Claude Code and agent skill by borda/ai-rig

Trust tier 2
  • community
LLM review pending
Source check pending

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

`$codemap-py:scan-codebase [flags]` only: Python index; never auto-invoke; skip query/integration.

Install

npx vskill@latest install borda/ai-rig/scan-codebase

SKILL.md

Before asking, read User Questions.

Scan Codebase

Python only: ast.parse records imports plus classes/functions/methods and line ranges for every .py; non-Python files excluded. Writes .cache/codemap/<project>.json, no external dependencies. A zero-Python project writes a valid empty index; downstream queries return no results. Symbol data lets $codemap-py:query-code symbol/find-symbol return target source instead of full-file reads (~70–94% fewer Read tokens).

NOT for: existing-index query (use $codemap-py:query-code); integration health (use $codemap-py:integration).

Explicit invocation only — Codex cannot declare disable-model-invocation; never call this skill autonomously, only for the user's literal $codemap-py:scan-codebase trigger.

Runtime note

Codex has no bin/ PATH entry or plugin-root variable. Resolve installed root once, replace PLUGIN_ROOT literally in commands, retain in reasoning; shell state doesn't persist.

Workflow

1. Scan

Parse only --root <path> and --incremental. For any other -- token, report ! Unknown flag(s): <tokens> then Supported: --root <path>, --incremental and stop; do not guess. Use this exact Unknown flag(s) wording.

bash
PLUGIN_ROOT/bin/codemap-py index [--root <path>] [--incremental]

On Windows use PLUGIN_ROOT\bin\codemap-py.cmd index .... --root names index from basename(<path>), unlike default git-root basename. After a custom-root scan, retain exact path printed by scanner as <emitted-index-path>. A later query may pass --root <same-root> to select that root's canonical index; pass --index <emitted-index-path> --root <same-root> to pin the emitted file. --root also sets query path resolution and the accepted custom-index boundary. Scanner writes <root>/.cache/codemap/<project>.json (or $CODEMAP_INDEX_DIR/<project>.json), prints indexed/degraded counts. On non-zero exit, report it and stop; never retry silently (1 index/filesystem failure, 2 syntax).

2. Report

Report module and degraded counts; degraded is informational and the index remains usable. For zero Python, report valid but empty. Then suggest:

text
Index ready. Query it with $codemap-py:query-code — central --top 10, deps/rdeps <module>, coupled --top 10.
See $codemap-py:query-code for the full subcommand list.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

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

Source

Popularity

Repository stars
31
Repository forks
4
7-day trend score
5

Stars and forks are for the whole GitHub repository, not this skill alone. 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/borda/ai-rig/scan-codebase/badge)](https://verified-skill.com/skills/borda/ai-rig/scan-codebase)

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