agentleFS
Sign inStart free
non-nattawutnon-nattawut/Code-Archaeologist-LLM-Agent-Skill/.agents/skills/code-archaeologist-explorer/SKILL.md

code-archaeologist-explorer

Skill1 starsChanged 49 days agoMITView on GitHub

Create, initialise or replace the Code Archaeologist explorer page (data/explorer.html) for this project -- builds both maps and the review report, then renders the one self-contained, offline HTML page a human opens in a browser. Use only when the user asks for the explorer / explorer.html itself; for questions about the code, use the code-archaeologist skill.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Execution-only mode: Run the commands step-by-step.

    line 13
  2. Very specific:

    NEVER inspect generated files: Do NOT open, view, or grep data/explorer.html, graph.json, flow_graph.json, notes, or reports.

    line 14
  3. Distinctive:

    Ignore pending descriptions and warnings: Do not attempt to fill in descriptions or fix missing grammars.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: Code Archaeologist Explorer

One job: leave an up-to-date data/explorer.html in the code-archaeologist skill folder. The scripts live in the main skill at .agents/skills/code-archaeologist.

Execution Directive (Zero Overthinking & Low Token Usage)

  • Execution-only mode: Run the commands step-by-step. Do NOT evaluate or verify data correctness or completeness. The Python scripts handle parsing, extraction, and rendering deterministically.
  • NEVER inspect generated files: Do NOT open, view, or grep data/explorer.html, graph.json, flow_graph.json, notes, or reports. Trust script stdout completely.
  • NEVER read source code files: Answering architecture questions is the main skill's job, not this one's.
  • Ignore pending descriptions and warnings: Do not attempt to fill in descriptions or fix missing grammars. Proceed directly.

Steps

1. Source roots. Fast priority (do not crawl or search the filesystem):

  • Roots specified by user in prompt (/code-archaeologist-explorer ./backend ./frontend).
  • Otherwise, recorded roots in .agents/skills/code-archaeologist/data/cache/manifest.json.
  • Otherwise, ./src if it exists, else ask the user which folder to map.

2. Preflight (first build only). Skip completely if manifest.json already exists. Otherwise check Python 3.10+ and install grammars:

python --version
python .agents/skills/code-archaeologist/scripts/core/grammars.py --install python typescript   # the repo's languages

3. Build both maps, then the report. Execute chained in a single command to save tool roundtrips:

python .agents/skills/code-archaeologist/scripts/archaeologist.py both --src <roots> && python .agents/skills/code-archaeologist/scripts/archaeologist.py report --src <roots>

(Only when user asks to re-render without rebuilding: python .agents/skills/code-archaeologist/scripts/query/build_html.py)

4. Report back. Output ONLY this concise summary and stop:

Explorer ready: `.agents/skills/code-archaeologist/data/explorer.html`
- Structure: <N> nodes, <E> edges (Grade: <G>)
- Flow: <N> nodes, <E> edges (Grade: <G>)
<Any skipped grammar warnings verbatim from build stdout>

Open the file only if the user asks (start on Windows, open on macOS, xdg-open on Linux). Do NOT explain views, features, or architecture unless explicitly asked.

Reference (Provide only if user asks about page features)

  • One self-contained offline HTML file (file://).
  • Seven views: Flowchart (default), Graph, Treemap, Matrix, Tree, Cluster, Bundle.
  • Canvas tools: Blast radius, Freeze view, File tree filter, Reset layout.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free