mark393295827/third-brain-v5-skills/agent-teams-command
Claude Code and agent skill by mark393295827/third-brain-v5-skills
- community
Checking that the SKILL.md file is still in the repository.
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command scaled from 5 to 100+ agents.
Install
npx vskill@latest install mark393295827/third-brain-v5-skills/agent-teams-commandSKILL.md
Agent Teams Command — 安德智能体集群指挥系统 (V8.1)
<skill_contract> <input>A mission with independently ownable workstreams, time SLA requirements, pre-flight task list, token budget, interfaces, permissions, and an integration owner.</input> <output>An isolated worker fleet (5 to 100+ agents), typed IPC ledger, pre-allocated token ledger, serial integration, cleanup, and evidence receipts.</output> <done>Pre-flight task list is 100% reconciled, integrated artifacts pass mission checks, token consumption is within TCLR boundaries, and cleanup gates pass.</done> <non_goals>Parallelism without a task list, unbounded token burn, overlapping writers, or worker self-certification.</non_goals>
Strategic intent and final integration remain serial; owned execution runs in dynamically scaled parallel squadrons (5, 10, 50, 100+ agents). Use the Ender lens for commander intent and squad autonomy, Palantir for operational objects/actions, and von Neumann for executable process architecture. Detailed patterns: references/ender-palantir-command-patterns.md; examples: references/classic-campaigns.md.
Usage Template
Provide: mission, time SLA, task list candidate, workstreams, scaling tier (5/10/50/100+), dependencies, acceptance criteria, token budget (ETC limit), permissions, runtime capabilities, and integration owner.
Workflow
<intake>
- Mission Intake & Scale Triage: Analyze mission complexity and select the smallest supported tier: Tier 1 (Squad: 5 agents), Tier 2 (Squadron: 10 agents), Tier 3 (Battle Group: 50 agents), or Tier 4 (Fleet: 100+ agents). If the runtime exposes fewer slots, cap the active fleet to that observed limit.
- Pre-flight Task List & Token Gate: Generate structured task list with explicit owner, territory, expected output, verification command, and token budget (ETC).
- Territory Mapping: Partition work into non-overlapping directories or git worktrees. Every worker gets strictly exclusive write boundaries.
</intake>
<unknowns_gate>
If dependencies, write ownership, or verification commands are ambiguous, return NEEDS_INPUT or INSUFFICIENT_EVIDENCE. Do not launch parallel workers before pre-flight task list and token ledger are fully reconciled.
</unknowns_gate>
<execute>
- Launch Workers: Dispatch workers in parallel across isolated worktrees. Each receives a typed
context_manifestcontaining only its objective, dependencies, territory, inputs, output schema, budget, and verifier. - Typed IPC & Command Board: Workers report state transitions (
pending->active->review->accepted->closed) to shared command board. - Independent Verification: Evaluator and reviewer agents verify worker outputs against objective criteria. No worker self-certification.
- Serial Integration & Join Gate: Integrator aggregates verified artifacts and receipts in dependency order. Do not merge private branch transcripts into the integration context. Run regression tests.
- Durable Write-back & Cleanup: Persist execution receipts, update system logs, and clean up temporary worktree branches.
For high-risk operations or cross-repo modifications, require independent review and human approval. Prepare a rollback plan before applying writes.
</execute>
<evaluate>
Audit total token consumption against the mission-declared TCLR: verified tasks resolved per 10,000 effective tokens consumed. Higher is better; do not invent a universal threshold. Verify all workstreams reached accepted or closed state, no file ownership conflicts occurred, and the declared regression suite passed.
</evaluate>
<retry_policy>
max_attempts: 2. Stop on repeated failure signature or NO_PROGRESS. If a worker stalls or fails, reassign territory or downgrade to serial execution rather than launching unbudgeted retries.
</retry_policy>
<state_contract>
Persist {mission_id, run_id, status, attempt, budget, token_ledger, task_list, worker_fleet, context_manifest, command_board, evidence, unknowns, next_action} in durable storage.
</state_contract>
Failure Protocol
NEEDS_INPUT: Ambiguous mission scope or overlapping territory; prompt for clarification before launch.INSUFFICIENT_EVIDENCE: Missing verification command or unverified worker output; reject merge.BLOCKED_PERMISSION: Worker lacks required tool or file write permission; escalate to commander.BLOCKED_DEPENDENCY: Upstream task failed; suspend dependent workers until resolved.VERIFY_FAILED: Artifact fails independent evaluation; reject and trigger bounded repair.NO_PROGRESS: Worker produces duplicate errors after 2 attempts; stop worker and flag for review.BUDGET_STOP: Token consumption exceeds allocated ETC budget; trigger automatic halt.max_attempts: 2.
Output Contract
Return status, result (worker fleet summary, task resolution ledger, and verified artifacts), evidence (source receipts, lint receipts, and integration logs), unknowns, and next_action including approval or rollback when relevant.
Edge Cases
- File Collision: Two workers attempt to modify the same file -> Integrator serializes execution and assigns one canonical owner.
- Worker Runaway: Worker exceeds token budget without progress -> Heartbeat monitor triggers instant
BUDGET_STOPkill. - Context Drift: Worker hallucinates outside its assigned territory -> Reviewer rejects output and logs territory violation.
Success Metrics
- 100% of pre-flight tasks resolved with verifiable evidence.
- Zero file write collisions across concurrent workers.
- Total token expenditure remains within allocated ETC budget.
- Wall-clock time reduced significantly compared to single-agent baseline.
Quality Gates
- [ ] Pre-flight task list and token ledger reconciled before execution.
- [ ] Exclusive write territories assigned to all active workers.
- [ ] Independent reviewer verified all deliverables (no self-certification).
- [ ] Integrator executed serial merge with passing regression suite.
- [ ] High-risk operations received independent review, human approval, and rollback readiness.
- [ ] Worktrees cleaned up and durable receipts written to system log.
</skill_contract>
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/agent-teams-command/SKILL.md
Popularity
- Repository stars
- 136
- Repository forks
- 19
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 28 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mark393295827/third-brain-v5-skills/agent-teams-command)