agentleFS
bex-cobex-co/bex/.claude/skills/rt-normalize-abstractions/SKILL.md

rt-normalize-abstractions

Skill576 starsChanged 17 days agoApache-2.0View on GitHub

Audits and fixes layering violations against the workspace import DAG (operator→types←backend; cli standalone; dashboard consumes the API, never reimplements it) and adds depguard rules so violations can't return. Use when the user asks to run the rt-normalize-abstractions routine, audit module boundaries, or fix layering violations.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After the verification phase, follow the shipping phase below without asking the user to invoke ship separately.

    line 15
  2. Very specific:

    Every change must pass the verification gates for the modules it touched before being reported as done: operator make test + make lint …

    line 19
  3. Very specific:

    Run npx prettier@3.4.2 --write on any markdown touched.

    line 20
  4. Distinctive:

    Before shipping, summarize results in commentary using: Fixed (file:line + one-line rationale) / Deferred (item + why) / Skipped (finding + …

    line 21
  5. Very specific:

    Check whether lego/backend/.golangci.yml and lego/operator/.golangci.yml encode the DAG in depguard rules (backend's depguard currently …

    line 31
  6. Very specific:

    Add depguard rules encoding the DAG to the golangci configs so make lint catches future violations.

    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

Routine: Abstraction Police

Enforce the layering: operator → types ← backend; types imports no sibling; cli imports no lego sibling; the dashboard talks to the backend only through its API client and never reimplements server-authoritative logic.

Routine ground rules

  • A user request to run this routine authorizes the full cycle: plan, fix, verify, then invoke $ship (Codex) or /ship (Claude) directly in the same run. Honor explicit user limits such as audit-only or no-ship.
  • Keep a concise execution plan in the conversation and update it as findings are confirmed. Continue into implementation without a planning approval pause. Do not create or file a .pm milestone/task as a prerequisite or substitute for fixing; use the board only if the user requests it.
  • After the verification phase, follow the shipping phase below without asking the user to invoke ship separately. Preserve the ship skill's branch, conflict-resolution, and safety rules.
  • Fix everything you find directly in the working tree. If a fix can't be finished safely in this run, revert only your partial work for that fix and list it under Deferred in the report — never leave the tree half-refactored.
  • Scope: parse $ARGUMENTS per Phase 1 — an optional path/module scope or skill-specific target. No argument = the skill's stated default (usually the whole repo via parallel agents per module: lego/types, lego/operator, lego/backend, lego/cli, dashboard).
  • False-positive discipline: if a finding is intentional, load-bearing, or ambiguous, skip it with a one-line reason — don't argue it into a change.
  • Every change must pass the verification gates for the modules it touched before being reported as done: operator make test + make lint (from lego/operator/), cd lego/backend && go test ./..., cd lego/cli && go test ./..., dashboard yarn test + typecheck.
  • Run npx prettier@3.4.2 --write on any markdown touched.
  • Before shipping, summarize results in commentary using: Fixed (file:line + one-line rationale) / Deferred (item + why) / Skipped (finding + reason) / Gates (commands run + outcomes).

Phase 1 — Scope

Parse $ARGUMENTS as an optional module/boundary. Empty = all boundaries.

Phase 2 — Mechanical audit

  • Per Go module, diff actual imports against the law: go list -deps ./... or grep -rn '"github.com/bex-co/bex/lego/'.
  • Within-module layer skips: cmd/ reaching deep into internals instead of the intended package surface.
  • Check whether lego/backend/.golangci.yml and lego/operator/.golangci.yml encode the DAG in depguard rules (backend's depguard currently guards the id convention). Missing DAG rules are themselves a finding.

Phase 3 — Semantic audit

Parallel agents compare dashboard logic against lego/backend/internal/apps: blueprint validation and pricing are the likely offenders. Logic that must stay server-authoritative (pricing, plan diffs, authz decisions) may not live client-side; the dashboard renders API answers.

Phase 4 — Fix

  • Wrong-direction or sideways imports → move the shared code to lego/types (the only module both operator and backend may import) and migrate callers.
  • Dashboard reimplementations → replace with API data (extend the GraphQL/REST response if a field is missing).
  • Add depguard rules encoding the DAG to the golangci configs so make lint catches future violations.

Phase 5 — Verify and report

Types moves ripple: run all Go gates; make lint must pass WITH the new depguard rules; dashboard gates if touched. Report per the standard format.

Final phase — Ship

After all required gates pass, read and execute the ship skill for the routine's completed changes. Stage only intended changes from this run; preserve unrelated work. Do not end at a plan, findings report, milestone, or request for shipping approval. If there are no changes, report that outcome without creating an empty commit. If a required gate remains blocked or fails after reasonable repairs, report the exact blocker and do not ship unverified changes.

Once the push succeeds, report the shipped HEAD SHA and subject per the ship skill and stop; do not monitor CI or deployment.

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.