agentleFS
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/topology-scaffolder/SKILL.md

topology-scaffolder

Skill1 starsChanged 12 days agoMITView on GitHub

Scaffolds the mandatory docs/ tree (roadmaps, sprints, architecture, contracts) and keeps active_state.json's Documentation Entry Point topology in sync. The only skill authorized to physically write project topology, on behalf of the Topology Mapper agent.

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:

    Constraint: Must avoid Mermaid for folder structures to prevent rendering collapse in complex trees.

    line 36
  2. Very specific:

    Blueprint Policy: Only the Topology Mapper agent is authorized to invoke this skill's write procedures.

    line 40
  3. Distinctive:

    Language Guard: All structural labels and state metadata MUST be in Technical English.

    line 41

≈ “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

🛠️ Local Skill: Topology Scaffolder (v1.0.0)

Domain

  • Category: Architecture / Scaffolding / State Tracking
  • Origin: Custom synthesis for automated project topology initialization.
  • Status: ACTIVE_LOCAL
  • Sovereignty: local (Project-Specific)

Technical Logic

This skill provides the Blueprint Engine for the framework. It handles the structural injection of the mandatory /docs/ tree and the surgical synchronization of the "Documentation Entry Point" (active_state.json) to ensure total project traceability.

Procedures

1. Mandatory Tree Injection (Hook Protocol)

  • Scaffolding Logic: Automatically creates the directory hierarchy:
    • /docs/roadmaps/[layer]/[app]/
    • /docs/sprints/[layer]/[app]/
    • /docs/architecture/
    • /docs/walkthroughs/
    • /docs/contracts/
  • Sovereignty: Overwrites or migrates legacy documentation structures to comply with the .agents standard.

2. State Synchronization (Coordinate Tracking)

  • Documentation Entry Point Update: Surgically modifies active_state.json to update:
    • active_layer: Current focus of the pipeline.
    • active_app: Target application under development.
    • current_sprint_id: The authoritative ID for the active session.

3. ASCII Infrastructure Mapping

  • Render Engine: Generates high-fidelity directory trees using ASCII characters.
  • Constraint: Must avoid Mermaid for folder structures to prevent rendering collapse in complex trees.
  • Optimization: Minimalist output to preserve token space while maintaining visual clarity.

Governance Audit

  • Blueprint Policy: Only the Topology Mapper agent is authorized to invoke this skill's write procedures.
  • Language Guard: All structural labels and state metadata MUST be in Technical English.

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.