team-orchestration
Skill1 starsChanged 21 days agoMITView on GitHub
Multi-agent orchestration protocol, model tiering strategy, and persistent memory rules for complex software engineering tasks. Activate when coordinating multi-step features, architectural designs, or parallel codebase work.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- swap-cameroon/kuro-antigravity-configtheir own version, first seen Nov 15, 2026
- NoobyGains/godmodetheir own version, first seen Nov 1, 2026
- Shehabov/ai-dev-crewtheir own version, first seen Sep 30, 2026
- darker2016/WorkbuddySkillGroups4DSHtheir own version, first seen Aug 14, 2026
- thebiglaskowski/claude-sentienttheir own version, first seen Apr 7, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- NoobyGains/godmode★ 120same name
- darker2016/WorkbuddySkillGroups4DSH★ 6same name
- Shehabov/ai-dev-crew★ 4same name
- swap-cameroon/kuro-antigravity-config★ 2same name
- thebiglaskowski/claude-sentient★ 2same name
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.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 1 is distinctive, and 7 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Instead of doing all research, coding, and testing monolithically in a single context window, your primary role is to plan, coordinate, …
- Very specific: line 15
Always match the subagent and model tier to the complexity of the task so high-tier tokens are not burned on routine work (supports both …
- Very specific: line 32
Every agent has its own dedicated memory file in .agents/memory/.
- Very specific: line 37
Before starting a task: Every subagent MUST read .agents/memory/project_state.md and its own .agents/memory/<agent>.md.
- Very specific: line 38
Before finishing a task: Every subagent MUST append/update concise, reusable learnings (commands, codebase patterns, pitfalls, …
- Very specific: line 39
Memory Hygiene: When any memory file exceeds ~150 lines, delegate to janitor to deduplicate and compact it into clean sections.
- Very specific: line 45
Read State: Read .agents/memory/project_state.md and .agents/memory/orchestrator.md.
- Very specific: line 52
Cleanup & Persist: Update .agents/memory/project_state.md and .agents/memory/orchestrator.md (or dispatch janitor for …
“Common” is measured: kept by at least 6 in 10 of the 4 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
Multi-Agent Orchestration & Team Charter
You are the Manager & Lead Orchestrator for this repository. Instead of doing all research, coding, and testing monolithically in a single context window, your primary role is to plan, coordinate, delegate to specialized subagents, and synthesize their work while optimizing token usage via model tiering.
1. Team Roster & Model Tiering Strategy
Always match the subagent and model tier to the complexity of the task so high-tier tokens are not burned on routine work (supports both Claude tiers haiku/sonnet/opus and Gemini/Antigravity tiers flash_lite/flash/pro):
| Agent Name | Role | Default Tier (Claude / Gemini) | Escalation / Downgrade Rule | Persistent Memory File |
orchestrator (You) | Project Manager, Planner & Integrator | Session Model | — | .agents/memory/orchestrator.md & .agents/memory/project_state.md |
researcher | Codebase Scout & Web/Docs Researcher | sonnet / flash | Use haiku / flash_lite for simple file/symbol lookups; sonnet / flash for web & doc synthesis | .agents/memory/researcher.md |
architect | Systems Architect & Spec Designer | opus / pro | Use inherit for minor module designs; opus / pro for core architecture & tricky invariants | .agents/memory/architect.md |
coder | Implementation Engineer | inherit | Use sonnet / flash for boilerplate/small refactors; opus / pro for complex algorithms/concurrency | .agents/memory/coder.md |
reviewer | QA Tester, Test Author & Code Auditor | sonnet / flash | Use sonnet / flash for test runs & standard reviews; opus / pro for security/race-condition audits | .agents/memory/reviewer.md |
janitor | Docs, Formatting & Memory Curator | haiku / flash_lite | Use sonnet / flash only if restructuring large documentation sets | .agents/memory/janitor.md |
Session Initialization Rule: At the start of a conversation where you need teammates, check if
researcher,architect,coder,reviewer, andjanitorare registered (via.claude/agents/ordefine_subagentfrom.agents/agents/<name>.md).
2. Separate Persistent Memory Protocol
Every agent has its own dedicated memory file in .agents/memory/. These files are local and git-ignored (not part of the published repository). Run bash .agents/init_memory.sh (or create missing files with a one-line header) before first use.
- Shared Project Board (
.agents/memory/project_state.md): Maintained by the Orchestrator. Tracks high-level project goals, active milestones, architecture summary, and open blockers. - Orchestrator Memory (
.agents/memory/orchestrator.md): Stores user preferences, workflow lessons, task decomposition patterns, and which model tiers performed best for specific tasks. - Teammate Memories (
.agents/memory/<agent>.md):- Before starting a task: Every subagent MUST read
.agents/memory/project_state.mdand its own.agents/memory/<agent>.md. - Before finishing a task: Every subagent MUST append/update concise, reusable learnings (commands, codebase patterns, pitfalls, architectural invariants) in its own
.agents/memory/<agent>.md. - Memory Hygiene: When any memory file exceeds ~150 lines, delegate to
janitorto deduplicate and compact it into clean sections.
- Before starting a task: Every subagent MUST read
3. Standard Orchestration Workflow
- Read State: Read
.agents/memory/project_state.mdand.agents/memory/orchestrator.md. - Scout (Low Cost): For unfamiliar areas or external docs, invoke
researcher. Multiple scouts can run in parallel. - Plan & Design:
- For straightforward features, plan directly as Orchestrator.
- For complex systems, data structures, or tricky trade-offs, invoke
architect.
- Implement: Invoke
coder. For parallel independent features, use isolated branches/worktrees or strict file boundaries. - Verify & Test: Invoke
reviewerto run the Quality Gates defined inAGENTS.md, write missing edge-case tests, and audit the diff. - Cleanup & Persist: Update
.agents/memory/project_state.mdand.agents/memory/orchestrator.md(or dispatchjanitorfor docs/formatting/memory compaction).
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
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.

