agentleFS
Sign inStart free
afaraha8403afaraha8403/balakit/.agents/skills/subsystem-walkthrough/SKILL.md

subsystem-walkthrough

Skill1 starsChanged 9 days agoMITView on GitHub

Walk through how a subsystem works: architecture, runtime flow, ownership, layering. Apply when the user asks "how does X work", "where should this live", or wants an onboarding mental model before changing code. Use design-rationale for motivation. Use dissect to audit entities. Use proving-change-safety before merging a change you do not trust.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When in doubt, take the simple path.

    line 37
  2. Distinctive:

    If the host cannot spawn subagents, run the slices sequentially yourself.

    line 50

≈ “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

Subsystem walkthrough

Leading words: mental model, one explainer, parallel slices, inherit host model.

Answer "how does X work?" at the level of a senior engineer onboarding onto the subsystem. Not annotated source.

Copy these steps into the todo list verbatim. Skip with skip: <reason>.

  1. Assess complexity. Simple → one explainer. Complex → 2–4 read-only explorers, then one synthesizer. Write Complexity: simple or Complexity: complex (N slices) as the first line of the output.
  2. Explore or explain (see below). Inherit the host model. Do not hardcode a slug.
  3. Present the explainer output with light edits only. Keep the Complexity line.

When in doubt, take the simple path.

Simple

One read-only subagent explores and explains in a single pass. Fill references/explainer-prompt.md without explorer findings.

Complex

Decompose into 2–4 distinct slices. Spawn explorers in one message, each with references/explorer-prompt.md. Then one synthesizer with the explainer template and every explorer's findings filled in. If the host cannot spawn subagents, run the slices sequentially yourself.

Output

First line: Complexity: simple or Complexity: complex (N slices).

Then: Overview / Key Concepts / How It Works / Where Things Live / Placement / Gotchas. Drop a section that does not apply. Placement is where new code for this subsystem should live (package, file, layer) — one short paragraph, not a second architecture essay.

Reply contract

The Complexity line, then the explanation. Do not rewrite it into a different structure after the explainer returns.

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