agentleFS
woodbearywoodbeary/later-dog/skills/laterdog/architect/SKILL.md

architect

Skill2 starsChanged 29 days agoApache-2.0View on GitHub

Plan a change before writing it: draft two or more designs that differ in who owns what, rule out the ones with structural problems, and pick the one that is right for the whole repository rather than the file you are in.

190 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation 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.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • jaydubya818Skill

    figure-it-out

    Use when novel or multi-phase work needs an auditable workflow and no narrower playbook fits.

    Also in 63 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 32 projects that use this

  • shiwenbin1617Skill

    ketchup-video

    Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.

    Also in 20 projects that use this

  • jaydubya818Skill

    poteto-mode

    Use when non-trivial work should follow the smallest rigorous Jstack workflow.

    Also in 37 projects that use this

  • +5 more from naman10parikh

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Use before a change that adds a concept, moves where some state lives, or crosses a module boundary.

    line 8
  2. Distinctive:

    Learn why it is shaped this way: Read the code you would change, its tests and its history (git log -p, the PR or job that introduced it).

    line 12
  3. Very specific:

    Build to the plan: When the code starts fighting it (the same workaround twice, a cast or any to get past the compiler, a lock to keep two …

    line 24

“Common” is measured: kept by at least 6 in 10 of the 178 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

Architect

Use before a change that adds a concept, moves where some state lives, or crosses a module boundary. A contained fix inside one module does not need it.

Procedure

  1. Learn why it is shaped this way. Read the code you would change, its tests and its history (git log -p, the PR or job that introduced it). Write today's design in a few lines: what owns which state, and who calls whom.
  2. Draft at least two designs that differ in ownership: where the state lives, which module decides, and which side of a boundary (desktop app, supervisor, cloud job, paired computer) does the work. Renaming or reshuffling files does not make a second design.
  3. Write each one from the caller's side first: the code a caller would write, then the types, then the modules and what each one knows.
  4. Rule designs out. A design is out as soon as one answer is no:
    • Does every fact (a list, a limit, a format, a token rule) live in one place, with everything else generated or derived from it? The skill exports generated from skills/laterdog/ are the pattern; hand-kept copies are not.
    • Does every piece of state have one writer? Job state, for example, is written only by the supervisor; everything else reads it through its API.
    • Is a retry, a restart or a lost response harmless? Nothing may run, submit, publish or notify twice.
    • Does it show what a backend cannot do instead of pretending? A native cloud task that cannot be cancelled stays "cancellation requested".
    • Does each process hold only the credential it needs? A dog gets its own derived token, never the admin token, and briefs carry no secrets.
    • Is each interface small next to what it hides, with one supported way to do each thing?
    • Does new later.dog behaviour get its own module under server/laterdog/ instead of growing a shared file such as server/index.ts?
  5. Choose, and write the choice down with the work (the PR description or the job brief): the designs considered, the question each one failed, and the test or fixture that will show the chosen one holds.
  6. Build to the plan. When the code starts fighting it (the same workaround twice, a cast or any to get past the compiler, a lock to keep two writers apart), go back to step 2 instead of patching around it.

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.