agentleFS
chadixearthchadixearth/graphyloop/skills/graphyloop-waves/SKILL.md

graphyloop-waves

Skill3 starsChanged 10 days agoMITView on GitHub

Use this skill when a request spans more than one layer (database + backend + frontend, or a feature plus a data pipeline). Turns the request into contract-first parallel waves with enforced dependencies, exclusive file ownership and per-lane acceptance checks, using the graphyloop planner and swarm.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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:

    NOT for a one-file change, a rename, or a single endpoint — fan-out only adds integration cost there.

    line 16
  2. Very specific:

    Plan, do not improvise: Call plan_feature / graphyloop_plan_feature with the user's request verbatim as goal.

    line 32
  3. Distinctive:

    every route: method, path, request shape, response JSON, error codes

    line 43
  4. Distinctive:

    test scenarios that define done (happy path + 2 edge cases per entity)

    line 45
  5. Distinctive:

    No implementation code in this wave.

    line 47
  6. Distinctive:

    Fan out a whole wave in ONE tool-call block: Every prompt carries: the contract and ctx pack paths, that lane's exclusive file list, its …

    line 52
  7. Distinctive:

    Integration is one wave, not a habit: Only Wave 2 may touch two lanes at once.

    line 60

≈ “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

Wave dispatch (contract-first fan-out)

Multi-layer work fails two ways: built serially it takes the sum of its lanes, and fanned out without a frozen contract it produces three incompatible versions of the same table. This skill is the third option.

When to activate

  • The request names two or more of: schema/data, API/server, UI/pages, import/export pipeline.
  • Words like "system", "app", "platform", "management", "dashboard + data".
  • NOT for a one-file change, a rename, or a single endpoint — fan-out only adds integration cost there.

The pipeline

Wave 0  context pack + contract   ONE agent, alone: ctx-<slug>.md, then contract-<slug>.md
Wave 1  builders      data ∥ backend ∥ frontend ∥ tests   (ONE tool-call block)
Wave 2  integration   drop mocks, real calls, env wiring, boot the happy path
Wave 3  verify        test ∥ typecheck/lint ∥ security ∥ performance ∥ review
Wave 4  deploy        preflight → preview → GATED production

Wall clock = Wave 0 + slowest builder + integration + slowest verifier. Never the sum.

Procedure

  1. Plan, do not improvise. Call plan_feature / graphyloop_plan_feature with the user's request verbatim as goal. It returns waves, tasks, per-lane owns globs, acceptance checks and dependsOn.
    • shape: no-fanout → stop. This is inline or single-builder work.
  2. Context pack, then freeze the contract (Wave 0). One batched read pass (parallel reads/greps) writes .opencode/chadi/ctx-<slug>.md next to the contract: per lane, path:line, the current code excerpt, and the pattern file to copy. Lanes start editing from it instead of rediscovering. Then one agent writes .opencode/chadi/contract-<slug>.md:
    • entities: columns, types, nullability, foreign keys, indexes
    • every route: method, path, request shape, response JSON, error codes
    • components/pages: props and route paths
    • test scenarios that define done (happy path + 2 edge cases per entity)
    • the env keys the feature needs No implementation code in this wave. If the contract is wrong later, stop and fix the contract — never let a lane drift from it silently.
  3. Dispatch by dependency, not by optimism. Pass plan.tasks to task_distribute. Dispatch ONLY the ids in dispatchNow. blocked entries name what they are waiting on.
  4. Fan out a whole wave in ONE tool-call block. Every prompt carries: the contract and ctx pack paths, that lane's exclusive file list, its acceptance check, and the turn-economy footer verbatim. Builder lanes (wave 1) get: Read the ctx pack and contract first, in ONE turn. Batch 2+ reads/searches into one parallel call; read with line ranges; never re-read a file; first edit by turn 5; do not run project-wide lint/test/build — the driver does. The wave-0 lane that writes the ctx pack and contract gets: Batch 2+ reads/searches into one parallel call; read with line ranges; never re-read a file; write the ctx pack and contract before anything else. Integration, verify and deploy lanes (they run tests and builds) get: Read the ctx pack and contract first, in ONE turn. Batch 2+ reads/searches into one parallel call; read with line ranges; never re-read a file.
  5. Record every result. task_record returns what the result unblocked — that is the trigger for the next wave. After a restart or compaction, swarm_state reports readyTasks, blockedTasks and per-wave counts.
  6. Integration is one wave, not a habit. Only Wave 2 may touch two lanes at once. Everywhere else, file ownership is exclusive.

Rules that keep it honest

  • The database lane runs alongside backend and frontend, not before them — the schema was already decided in Wave 0. "DB first, then the rest" is the serial trap this skill exists to avoid.
  • Tests are written in Wave 1 from the contract's scenarios. A test authored after the code asserts whatever the code happens to do.
  • Frontend builds against mocks shaped like the contracted responses, with the fetch layer in ONE module so the integration swap is a single file.
  • Two edit-capable agents never own the same file in the same wave. Assign the ownership table before dispatch.
  • At most 4 concurrent build/test lanes by default; read-only verifiers may run wider; never poll a long-running job: background it.
  • A wave is not done because its agents returned. It is done when its acceptance check has been run and its output quoted.

Reporting

Report the wave table, then per lane: files touched, acceptance check run, and the decisive output line. Store one memory entry with the shape and wall time (PLAN shape=... lanes=... wall=...) so the next same-shape request can be compared instead of re-argued.

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.