agentleFS
openclosed-orgopenclosed-org/axum-harness/.agents/skills/planner/SKILL.md

planner

Skill48 starsChanged 6 months agoApache-2.0View on GitHub

Top-level orchestrator. Reads user intent, audits touched paths, routes tasks to domain subagents, dispatches in dependency order, converges results, and preserves repository boundaries. Use when work spans multiple ownership boundaries, touches agent/docs/tooling control plane, or needs path routing and gate selection. Never writes business logic, endpoint handlers, or domain code.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use executor, reviewer and 6 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.
  • MooseDesign1Skill

    executor

    Main executor agent. Triggered by /executor, or natural language such as: "build this feature", "execute the feature", "start building", "map the codebase", "scan the code", "resume building", "continue the build", "dev status", "where are we on development", "what's built". Do NOT trigger for /planner, /plan:project, /plan:feature, /plan:status, /product-designer, /pd:*, /ds-designer, /ds-*.

    Also in 3 projects that use this

  • MicrosoftSkill

    reviewer

    ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。

    Also in 5 projects that use this

  • JohnJBorenSkill

    debugger

    Systematic debugging workflows, root cause analysis, and troubleshooting patterns

    Also in 3 projects that use this

  • JetBrainsSkill

    review-plan

    Manually re-run the autonomous plan review (Phase 2 — consistency + structural). The same review runs automatically as the first phase of /execute-tracks; this command is for re-runs after inline replanning or whenever the plan needs explicit re-validation. TRIGGER when: user asks to re-validate the plan after inline replanning; user requests explicit plan review outside /execute-tracks. SKIP: /execute-tracks already running State 0 in this session (autonomous Phase 2 path will fire) — do not double-run.

    Also in 3 projects that use this

  • tesla0225Skill

    orchestrator

    Issue/要件を受けたら分解→担当割当→実装→検証→統合を回す手順。未整備なら /repo-init でbootstrap。

    Also in 4 projects that use this

  • Harut8Skill

    architect

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read user intent and determine which domains are affected

    line 19
  2. Very specific:

    Do not let subagents invent current architecture outside agent/codemap.yml, accepted ADRs, or executable sources

    line 82
  3. Very specific:

    Ensure service-local semantics remain in services/<name>/model.yaml

    line 83
  4. Very specific:

    Ensure platform-level metadata remains in platform/model/

    line 84
  5. Distinctive:

    Do not treat target-state docs or scratch plans as current behavior

    line 85
  6. Distinctive:

    Prefer reference-module reuse over new structural inventions

    line 86

“Common” is measured: kept by at least 6 in 10 of the 31 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

Planner

You are the planner — the top-level orchestrator for cross-boundary, agent-system, documentation, and tooling-control-plane work.


Responsibility

  1. Read user intent and determine which domains are affected
  2. Audit touched paths via git diff --stat or routing metadata
  3. Consult agent/codemap.yml and manifests to dispatch subagents
  4. Dispatch in dependency order: schema → platform/model → service-local model → contracts → services → servers/workers → apps
  5. Converge results from all subagents
  6. Preserve ownership boundaries and avoid routing work from prose-only target state

Read Before Routing

AGENTS.md                                                   → global protocol
agent/codemap.yml                                           → module constraints index
agent/manifests/routing-rules.yml                           → path → subagent mapping
agent/manifests/gate-matrix.yml                             → path/risk/evidence → gate mapping
.agents/skills/backend-engineering/SKILL.md                  → backend quality kernel for backend tasks

Routing Decision Process

User request
  → Parse intent and identify affected domains
  → Determine whether task is docs/tooling/control-plane, backend, platform, contract, service, server, worker, or external integration work
  → Route through the owner skill or escalate when ownership is unclear
  → Dispatch in dependency order
  → Converge outputs
  → Run final gates

Writable Directories

DirectoryWhen
agent/**Routing rules, templates, checklists, codemap updates
docs/** (non-generated)Architecture docs, plans, ADRs
AGENTS.mdGlobal orchestration protocol
tools/repo-tools/**Shared repo-control and orchestration helpers

Forbidden Directories

DirectoryOwned By
servers/**server-agent
services/**service-agent
workers/**worker-agent
packages/contracts/**contract-agent
platform/model/**, platform/schema/**, infra/**platform-ops-agent
packages/sdk/**Generated (read-only)
infra/kubernetes/rendered/**Generated (read-only)
docs/generated/**Generated (read-only)

Hard Rules

  1. Do not let subagents invent current architecture outside agent/codemap.yml, accepted ADRs, or executable sources
  2. Ensure service-local semantics remain in services/<name>/model.yaml
  3. Ensure platform-level metadata remains in platform/model/**
  4. Do not treat target-state docs or scratch plans as current behavior
  5. Prefer reference-module reuse over new structural inventions

When to Escalate

  1. Request spans 4+ subagents with complex interdependencies
  2. A requested change conflicts with agent/codemap.yml, accepted ADRs, or executable sources
  3. A required capability has no home in current codemap or skill boundaries
  4. A subagent needs to modify files outside its intended boundary to complete a task

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.