agentleFS
ai-erp-collabai-erp-collab/deterministic-context-routing-plugin/skills/add-module/SKILL.md

add-module

Skill0 starsChanged 4 days agoMITView on GitHub

Use when the user asks to add, register, or create a module in an existing context-routing workspace, for example "add module billing with sources in src/billing". Registers it in modules.md, creates its folders and session log, and writes its inventory. Not for first-time setup (use init) and not for writing curated pages (use curate).

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If tools/kb/kb.py is missing but AGENTS.md and modules.md exist, the workspace predates the integrity tool: tell the user to run the init …

    line 15
  2. Very specific:

    Read modules.md. If the name or any alias is already registered, stop and report the clash.

    line 21
  3. Very specific:

    Leave out the evidence: line when the user named no folder.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

Add Module

Inputs: a short lowercase module name, a one-line purpose, the source paths it covers, and aliases. ASK for anything missing; propose aliases from the name and purpose and let the user confirm. ASK also for the module's evidence folders: where outside material for it lands (table exports, library sources, usage examples, documents). "None" is a valid answer.

If tools/kb/kb.py is missing but AGENTS.md and modules.md exist, the workspace predates the integrity tool: tell the user to run the init skill, which upgrades it, and stop.

Steps

  1. Read modules.md. If the name or any alias is already registered, stop and report the clash.
  2. Append the module to modules.md:

    - <module>
      - path: `modules/<module>/`
      - wiki: `knowledge-base/modules/<module>/`
      - shared wiki: `knowledge-base/shared/`
      - sources: `<source path>`, `<source path>`
      - evidence: `<folder>`, `<folder>`
      - artifacts: `source-artifacts/`
      - aliases: <alias>, <alias>

    Leave out the evidence: line when the user named no folder. Every file under an evidence folder is then tracked by the integrity tool.

  3. Copy assets/module/ (in this skill's folder) to modules/<module>/ and assets/wiki/ to knowledge-base/modules/<module>/. In the copied files replace ExampleModule and example-module with the module name. Write the purpose into the module idea.md.
  4. In modules/<module>/session_state.md, replace the template entry with a first entry: module registered, sources listed, next action "inventory". End it with <!-- AGENT-SESSION-STOP -->.
  5. Inventory. Read in full every artifact listed for this module in source-artifacts/INDEX.md, and the module's source paths. For a file over about 50 KB, start from python tools/kb/kb.py outline <file> and read it span by span until every part is covered. Write knowledge-base/modules/<module>/inventory.md: one line per named item (table, field group, function, class, flag, constant, naming rule, constraint) with the file it came from. Do not rank or skip anything; curation later selects from this list, and an item missing here is easy to lose for good. If the sources are too large for one session, ASK whether to split, and record which files are done in the module session log. Add inventory.md to the module INDEX.md.

Finish with the close-session skill for this module.

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.