orchestrate
Skill334 starsChanged 34 days agoMITView on GitHub
Decompose a goal and orchestrate APC subagent workers to execute it in parallel, then verify and integrate results. Use when the user invokes /apc-orchestrate, the skill action `orchestrate`, or asks to delegate/fan out/split work across subagents.
161 other projects use a version of this.
Adopted by
Most recently taken up by
- alexratmanpl/business-agent-skillstheir own version, first seen Nov 8, 2026
- gtonkov/claude-codetheir own version, first seen Nov 8, 2026
- edilsonvilarinho/usage-monitortheir own version, first seen Nov 8, 2026
- nathanonn/agent-skillstheir own version, first seen Nov 8, 2026
- peterpme/skillstheir own version, first seen Nov 8, 2026
- GDriem/agent-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use define-requirements, orchestrate-plan 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.
sson0-erSkilldefine-requirements
Work with the user, one question at a time, to complete the requirements document (docs/claudex/<slug>/01-requirements.md). Run by the orchestrator (parent). Stays out of design and implementation.
Also in 3 projects that use this
EternallLightSkillorchestrate-plan
Use when executing a locked, reviewed PLAN.md by delegating the implementation to visible worker agents in Orca, herdr, or cmux ONE PHASE at a time — splitting the plan into context-window-sized phases, giving every phase a pristine worker context, and (when the plan touches INDEPENDENT repos) running one worker per repo IN PARALLEL. Triggers on "run the plan with a worker", "execute the plan in the other pane", "split the plan into phases and build it with workers", "build the backend and frontend in parallel panes". Not for edits you can finish inline; outside Orca, herdr, or cmux use tgc-skills:orchestrate.
Also in 3 projects that use this
sson0-erSkillrecord-evidence
How to record external facts (docs, command output, codebase findings) as evidence and design choices as decisions. Used by the researcher, designer and reviewer agents.
Also in 3 projects that use this
PinkneyJiangSkillimprove-architecture
扫描代码库中的架构摩擦点,识别浅模块并挖掘深模块演进机会。生成可视化交互式 HTML 诊断报告,并在用户确认后闭环实施深度重构。
Also in 4 projects that use this
kjnezSkillticket
Work on a JIRA/Linear ticket end-to-end: read ticket details, explore codebase, create a branch, implement with TDD, run quality checks, update ticket status, and create a PR. Use when the user provides a ticket ID to implement. Triggers on requests like "/ticket PROJ-123", "work on this ticket", "implement PROJ-123".
Also in 4 projects that use this
xfstudioSkillreverse-engineer
Expert reverse engineer specializing in binary analysis,
Also in 3 projects that use this
Other versions161 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 161
- Significant-Gravitas/AutoGPT★ 188ksame name
- rohitg00/pro-workflow★ 2.9ksame name
- apmantza/pi-lens★ 521same name
- boshu2/agentops★ 453same name
- quantumaikr/quant.cpp★ 403same name
- kagenti/kagenti★ 303same name
- varun29ankuS/shodh-memory★ 294same name
- provencher/codex-skills★ 271same name
- first-fluke/fullstack-starter★ 226same name
- sd0xdev/sd0x-dev-flow★ 192same name
151 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/no-ai-attribution.mdcCursor rule
- apc-setupSkill
- audio-plugin-coderSkill
- debugSkill
- designSkill
- dreamSkill
- implSkill
- planSkill
- shipSkill
- skill-debugSkill
- skill-designSkill
- juce-webview-windowsSkill
- skill-ideationSkill
- skill-implementationSkill
- skill-packagingSkill
- skill-planningSkill
- skill-testingSkill
- skill-troubleshootingSkill
- testSkill
- apc-setupSkill
- skill_debugSkill
- skill_designSkill
- dreamSkill
- implSkill
- orchestrateSkill
- planSkill
- shipSkill
- juce-webview-windowsSkill
- skill_testingSkill
- skill_troubleshootingSkill
- testSkill
- audio-plugin-coderSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 144 edited versions we read keep these.
5
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
- Distinctive: line 36
Use your host's native subagent mechanism and select the profile by name:
- Distinctive: line 78
Every task you hand to a worker must state:
- Distinctive: line 83
All needed context — workers are stateless and cannot see this conversation.
- Very specific: line 92
Read AGENTS.md (and .agents/rules/juce-build-protocols.md for plugin code work) before writing worker briefs, and enforce those rules …
- Distinctive: line 101
If the goal is smaller than the delegation overhead, say so and offer to do it directly — but default to delegating since the user invoked …
- Distinctive: line 104
Keep the user informed: one short line per wave, not play-by-play.
“Common” is measured: kept by at least 6 in 10 of the 144 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.
Files
Orchestrate — Subagent Delegation
Trigger: /apc-orchestrate <goal> (skill action orchestrate)
You are the orchestrator. Do NOT do the implementation work yourself — decompose the goal into subtasks, assign them to worker subagents, then verify and integrate their results.
The goal is whatever the user typed after the command. If no goal is given, ask for one and stop.
Worker profiles
Canonical definitions live in .agents/agents/*.md. Per-host
adapters are generated by scripts/sync-agents.ps1 / .sh — if a
worker profile is unavailable in your host, run the sync script once.
| Profile | Tier intent | Use for |
cheap-worker | low cost | Search, extraction, exploration, formatting, simple edits |
standard-worker | default | Implementation, routine debugging, refactoring, tests, review |
deep-worker | strong | Multi-step, ambiguous, cross-component, concurrency |
expert-worker | escalation only | After verified failure of a lower tier |
Codex parity: .codex/agents/*.toml (underscores: cheap_worker …)
plus scripts/codex/apc-codex-run.* tier routing — see
docs/codex-orchestration.md.
Spawning per host
Use your host's native subagent mechanism and select the profile by name:
- Devin CLI —
run_subagent(.agents/agents/*.mdis read natively); background for parallel waves. - Claude Code — Task/subagent with
.claude/agents/profiles. - OpenCode — subagent mode with
.opencode/agent/profiles. - Cursor / Kilo — Task/subagent or mode delegation; pass the worker definition contents as the subagent brief if profiles are not registered.
- Hosts without subagents — dispatch workers as headless runs via
scripts/codex/apc-codex-run.ps1/.sh(Codex CLI) or execute the subtasks sequentially yourself; say which fallback you used.
Workflow
- Preconditions — confirm an APC checkout (
templates/,scripts/,CMakeLists.txt). If the goal touches a plugin, read<plugins_dir>/<PluginName>/status.jsonfirst and respect phase gates — never have a worker edit a frozen (ship_complete) plugin. - Decompose — split the goal into self-contained subtasks with DISJOINT file sets. Two write-capable workers may never touch the same file or directory; merge or sequence tasks that collide.
- Wave 0 — research — if workers need context you lack, spawn
cheap-worker/deep-workerresearch tasks first; fold findings into the write-task briefs. - Wave 1 — execute — run write-capable workers in parallel, max 3 concurrent (parallel workers multiply spend). Independent tasks always run concurrently, never sequentially.
- Wave 2 — verify — after writes land, run the narrowest real
check:
node bin/apc.js build <Name>(preferred) orscripts/build-and-install.ps1/.shfor plugin work; targeted tests or lint for repo work. Prefer objective verification over worker self-assessment. - Integrate & report — collect every worker's report, resolve
small conflicts yourself, retry/escalate failed tasks one tier up
(
deep-worker, thenexpert-worker), then deliver one consolidated summary: per-worker outcome, files changed, verification result, leftovers.
Worker brief contract
Every task you hand to a worker must state:
- Repo root and the APC plugin path (
Get-ApcPluginPath), if relevant - The exact deliverable and definition of done
- File boundaries: which paths it owns, which it must NOT touch
- All needed context — workers are stateless and cannot see this conversation; they also cannot ask the user questions
- Relevant APC rules:
ui_frameworkfromstatus.json, PowerShell vs Bash by OS, no rawcmake, noCo-authored-byAI trailers - Required report format back to you
Rules
- Track the task DAG with the host's todo/plan tool.
- Read
AGENTS.md(and.agents/rules/juce-build-protocols.mdfor plugin code work) before writing worker briefs, and enforce those rules inside the briefs. - Preserve
ui_framework: Visage tasks never produce WebView files and vice versa — state it explicitly in the brief. - Resolve ambiguity with the user BEFORE spawning; workers cannot ask questions.
- Back up plugin state (
Backup-PluginState/backup_plugin_state) before delegating implementation or packaging changes. - If the goal is smaller than the delegation overhead, say so and offer to do it directly — but default to delegating since the user invoked this command expecting it.
- Keep the user informed: one short line per wave, not play-by-play.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

