agentleFS
scolladonscolladon/craft/skills/architecture/SKILL.md

architecture

Skill2 starsChanged 34 days agoMITView on GitHub

Craft architecture phase - run the repo's boundary-check harness over the change, triage violations (fix the edge or document an exception); gates the PR. Also useful standalone.

139 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use intelligent-routing, bash-linux and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SKB3002Skill

    intelligent-routing

    Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

    Also in 6 projects that use this

  • xenitV1Skill

    bash-linux

    Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

    Also in 8 projects that use this

  • xenitV1Skill

    red-team-tactics

    Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

    Also in 8 projects that use this

  • SKB3002Skill

    nextjs-react-expert

    React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.

    Also in 3 projects that use this

  • +8 more from xenitV1

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 121 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Every resolved technique command — declared or derived — is trusted operator input (same trust model as the manifest and context: files).

    line 25
  2. Very specific:

    Verify the triager's commit.

    line 47
  3. Distinctive:

    Impacts: fold or defer at discovery: when the triage result lands.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 121 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

craft:architecture

Preamble (always runs — non-overridable)

  1. Manifest read (lint if standalone). Standalone: scope = current branch vs default branch.
  2. Resolve the active technique set from phase.harness (the resolved descriptor), using the same ADR-149 discovery precedence — default-off favours no-op:

    • Declared — phase.harness.techniquePlan (engine-emitted) wins outright: each entry specifies technique id, run command, mode (gate | triage), optional scope, optional triage-procedure ref. run-style defaults to sync.
    • Derived — absent a declaration, read the repo's own boundary-check conventions (README / CONTRIBUTING / craft config) and derive one technique per documented dependency/import-boundary validation command, each GATE or TRIAGE per its nature.
    • No-op (terminal) — absent any declared or derived technique: record NO-OP(architecture): no techniques declared/probed and release the propose-gate entry; the phase ends here. This phase is default-off; no-op is the expected outcome in most repos.

    Every resolved technique command — declared or derived — is trusted operator input (same trust model as the manifest and context: files); the derived tier reads the repo's own committed conventions, never an untrusted external source.

    For each resolved technique, run its probe (config-file presence / binary resolvable). A failed probe declines the technique by absence: NO-OP(architecture:<technique-id>): declined — probe absent. When every technique is declined: the phase ends here and also appends the exact NO-OP(architecture): all techniques declined — <ids> line, the one a rebuild reads as the propose-gate release (per-technique lines never release it).

Procedure (default body — a manifest override: replaces everything below)

  1. Per-active-technique walk (run-style: sync default — no lock against teardown). For each technique in the resolved active set, scope per the technique's scope (default: the change's touched code, never wider). Capture the violation/finding report.
  2. The PR waits for triage (orchestrator invariant): on a non-empty finding set, spawn craft:harness-triager with: the findings; the gate; the commit message fix(architecture): <technique-id> <scope> (or chore(architecture): <technique-id> <scope> for an exception-only landing); global + architecture-phase context: files verbatim; the technique's triage-procedure ref (if declared).
  3. Verify the triager's commit; run the phase gate; record per-finding outcomes in the run record. A triager IMPACT( line gets its verdict under the run skill invariant Impacts: fold or defer at discovery when the triage result lands; EXCEPTION semantics are unchanged.

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.