OMA Multi-Agent Orchestrator
first-fluke/oh-my-agent
Splits a complex feature into prioritized tasks, spawns specialist CLI subagents in parallel, tracks them through shared memory and verifies each result.
Agent Teams orchestration patterns for multi-agent SAFe workflows.
Install Team Coordination
$ npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bybren-llc/safe-agentic-workflow team-coordination --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/team-coordination .claude/skills/team-coordination && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "team-coordination" agent skill from https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordination into .claude/skills/team-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-coordination", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordinationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bybren-llc/safe-agentic-workflow team-coordination --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/team-coordination .agents/skills/team-coordination && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "team-coordination" agent skill from https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordination into .agents/skills/team-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-coordination", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bybren-llc/safe-agentic-workflow team-coordination --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/team-coordination .cursor/skills/team-coordination && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "team-coordination" agent skill from https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordination into .cursor/skills/team-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-coordination", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bybren-llc/safe-agentic-workflow.git --path .agents/skills/team-coordination--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bybren-llc/safe-agentic-workflow team-coordination --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/team-coordination .gemini/skills/team-coordination && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "team-coordination" agent skill from https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordination into .gemini/skills/team-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-coordination", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bybren-llc/safe-agentic-workflow team-coordinationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/team-coordination .github/skills/team-coordination && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "team-coordination" agent skill from https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordination into .github/skills/team-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-coordination", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bybren-llc/safe-agentic-workflow team-coordination --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/team-coordination .opencode/skills/team-coordination && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "team-coordination" agent skill from https://github.com/bybren-llc/safe-agentic-workflow/tree/main/.agents/skills/team-coordination into .opencode/skills/team-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "team-coordination", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
team-coordination- GitHub stars
- 423
- Token cost
- ~1.7k tokens
- SKILL.md length
- 457 words
- Files
- 4 (incl. scripts, references, assets)
- Skills in repo
- 42
- Repo updated
- First seen
- Licence
- MIT
At a glance
Agent Teams orchestration patterns for multi-agent SAFe workflows.
- Spawning agent teams
- SKILL.md covers Purpose, Prerequisites, When This Skill Applies and Agent Teams vs Subagents vs…, plus 6 more sections
- Coordinating teammates
- Enforcing quality gates via task dependencies
What it does
Team Coordination is an agent skill from bybren-llc/safe-agentic-workflow. Agent Teams orchestration patterns for multi-agent SAFe workflows. Use when spawning agent teams, coordinating teammates, enforcing quality gates via task dependencies, or orchestrating the 11-agent SAFe pipeline. Covers team creation, messaging, shared task lists, and SAFe gate enforcement. Do NOT use for single-agent or simple subagent workflows.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts, reference files and assets.
It sits in Agent Workflows, covering Quality gates, Subagents and Multi-agent orchestration. The repository describes itself as: SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams (Now With AI-DLC!)… The licence is MIT.
When your agent uses it
- Spawning agent teams
- Coordinating teammates
- Enforcing quality gates via task dependencies
- Orchestrating the 11-agent SAFe pipeline
Example prompts
- “/team-coordination”
What it can do on your machine
Read from SKILL.md and the folder at commit 26ca58b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Team Coordination loads about 1.7k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 457 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from bybren-llc/safe-agentic-workflow at commit 26ca58b, republished under its MIT licence (© bybren-llc). 457 words, ~1,707 tokens.
Download SKILL.mdSave it as
.claude/skills/team-coordination/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- team-coordination
- description
- Agent Teams orchestration patterns for multi-agent SAFe workflows. Use when spawning agent teams, coordinating teammates, enforcing quality gates via task dependencies, or orchestrating the 11-agent SAFe pipeline. Covers team creation, messaging, shared task lists, and SAFe gate enforcement. Do NOT use for single-agent or simple subagent workflows.
Team Coordination Skill
TEMPLATE: This skill uses
{{PLACEHOLDER}}tokens. Replace with your project values before use.
Purpose
Orchestrate multi-agent teams for SAFe workflows. This skill provides patterns for spawning teams, assigning work by role, enforcing quality gates via task dependencies, and managing the full delivery pipeline.
Prerequisites
Agent Teams may be experimental depending on provider. Enable as required:
// Provider-specific settings
{
"env": {
"AGENT_TEAMS_ENABLED": "1"
}
}When This Skill Applies
- Orchestrating work across multiple agent roles (FE, BE, QAS, etc.)
- Spawning a team for a Feature or Epic-level deliverable
- Coordinating parallel implementation with quality gate enforcement
- Running competing hypothesis debugging with multiple agents
- Performing parallel code review across security, performance, and test coverage
Agent Teams vs Subagents vs Background Agents
| Approach | Communication | Coordination | Best For |
|---|---|---|---|
| Agent Teams | DMs, broadcasts | Shared TaskList with dependencies | Complex multi-role SAFe workflows |
| Subagents | Report back only | Main agent manages | Focused tasks, results only |
| Background Agents | None | None | Fire-and-forget parallel work |
Use Agent Teams when: teammates need to share findings, challenge each other, and coordinate via SAFe gates. Use Subagents when: you need quick, focused workers that report back. Use Background Agents when: tasks are independent and do not need coordination.
SAFe Team Patterns
Pattern 1: TDM as Team Lead
The TDM (Technical Delivery Manager) is the natural team lead in the 11-agent model:
Create an agent team for {{TICKET_PREFIX}}-XXX implementation.
Team lead (TDM) responsibilities:
- Spawn teammates by role (BE, FE, QAS, etc.)
- Create tasks with SAFe gate dependencies
- Monitor progress and steer teammates
- Synthesize results and escalate blockers
Spawn these teammates:
- BE Developer: Implement API endpoints per spec
- FE Developer: Implement UI components per spec
- QAS: Validate acceptance criteria after implementationPattern 2: Task Dependencies for Quality Gates
Use task dependencies to enforce the SAFe pipeline:
Task structure for {{TICKET_PREFIX}}-XXX:
1. "Implement API endpoint" (owner: be-developer)
2. "Implement UI components" (owner: fe-developer)
3. "QAS validation" (owner: qas, blockedBy: [1, 2])
4. "Create PR" (owner: rte, blockedBy: [3])
5. "Stage 1 review" (owner: system-architect, blockedBy: [4])
This enforces: Implementation -> QAS -> RTE -> Architect ReviewPattern 3: Spawning Teammates by Role
Map harness agent roles to teammate configurations:
Spawn teammates with role-specific prompts:
BE Developer teammate:
- Load: api-patterns, rls-patterns skills
- Task: Implement endpoints per spec at specs/{{TICKET_PREFIX}}-XXX-spec.md
- Constraint: All DB operations must use RLS context helpers
FE Developer teammate:
- Load: frontend-patterns skill
- Task: Implement UI per spec
- Constraint: Follow component patterns in patterns_library/ui/
QAS teammate:
- Load: testing-patterns skill
- Task: Execute testing strategy from spec
- Constraint: Must verify all acceptance criteria before approvingPattern 4: Parallel Code Review
Create an agent team to review PR #XXX. Spawn three reviewers:
- Security reviewer: Focus on RLS enforcement, input validation, auth checks
- Architecture reviewer: Focus on pattern compliance, separation of concerns
- Test reviewer: Focus on test coverage, edge cases, acceptance criteria
Have them each review independently, then share and challenge findings.Pattern 5: Competing Hypothesis Debugging
Users report [issue description]. Spawn 3-4 teammates to investigate:
- Teammate 1: Investigate [hypothesis A]
- Teammate 2: Investigate [hypothesis B]
- Teammate 3: Investigate [hypothesis C]
Have them talk to each other to challenge and disprove theories.
Update findings as consensus emerges.Communication Patterns
Direct Messages (Most Common)
Send a message to the BE developer:
"The API endpoint needs to handle pagination. Check patterns_library/api/
for the standard pagination pattern before implementing."Broadcast (Use Sparingly -- Expensive)
Broadcast to all teammates:
"STOP: Architecture decision changed. The auth middleware now uses
{{AUTH_PROVIDER}} session tokens instead of JWT. Check the updated
spec before continuing."Only broadcast for:
- Critical blocking issues
- Architecture changes affecting everyone
- Stop-the-line announcements
Shutdown Coordination
When all tasks are complete:
1. Send shutdown request to each teammate
2. Wait for approval from each
3. Clean up team resourcesQuality Gate Hooks
Show full SKILL.md (182 more words)Show less
TeammateIdle Hook
Validates teammates completed their work before going idle. Configure hook to return exit code 2 to send feedback and keep the teammate working.
TaskCompleted Hook
Validates task output meets criteria before allowing completion. Configure hook to return exit code 2 to prevent completion and send feedback.
Team Sizing Guidelines
| Work Scope | Recommended Size | Tasks per Teammate |
|---|---|---|
| Single Story | 2-3 teammates | 3-4 tasks each |
| Feature (multi-story) | 3-5 teammates | 5-6 tasks each |
| Epic (parallel features) | 5-8 teammates | 5-6 tasks each |
Rules of thumb:
- Start with fewer teammates; scale up if needed
- Each teammate should own different files (avoid conflicts)
- 5-6 tasks per teammate keeps everyone productive
- More than 8 teammates rarely helps (coordination overhead)
Known Limitations
- Experimental: May require feature flag to enable
- No session resumption: Resuming may not restore in-process teammates
- One team per session: Clean up before starting a new team
- No nested teams: Teammates cannot spawn their own teams
- Permissions inherit: All teammates start with lead's permission mode
- Token cost: Significantly higher than single session
Authoritative References
- Harness Agents:
AGENTS.md - Team Config:
.claude/team-config.json(if applicable) - Agent Workflow SOP:
docs/sop/AGENT_WORKFLOW_SOP.md
© bybren-llc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts, references, assets) in .agents/skills/team-coordination of bybren-llc/safe-agentic-workflow.
- SKILL.md
- assets/.gitkeep
- references/.gitkeep
- scripts/.gitkeep
Open the folder on GitHubat commit 26ca58b
Compare with similar skills
Team Coordination next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Team Coordination this skillbybren-llc/safe-agentic-workflow | 423 | — | ~1.7k | Automated safety check: Pass | MIT | |
| OMA Multi-Agent Orchestratorfirst-fluke/oh-my-agent | 1.3k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Swarm Parallel Dispatchlangchain-ai/langchain-skills | 1.3k | — | ~3k | Automated safety check: Pass | MIT | |
| NelsonAspegio/nelson | 421 | — | ~11k | Automated safety check: Warn | MIT | |
| Cursor Orchestratecursor/plugins | 10k | — | ~1.1k | Automated safety check: Pass | None | |
| Launching Agent Teamslexler/skill-factory | 239 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Swarm Parallel Dispatch
langchain-ai/langchain-skills
Fans a list of independent items out to subagents in parallel, merges the results back into a table and supports retrying only the rows that failed.
Nelson
Aspegio/nelson
Orchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down.
- Official
Cursor Orchestrate
cursor/plugins
Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.
Launching Agent Teams
lexler/skill-factory
Plans and launches Claude Code agent teams with distinct roles, right-sized tasks and detailed spawn prompts, and says when subagents or worktrees fit better.
Agent Teams Playbook
KimYx0207/Kim_Service
Cross-runtime playbook for multi-agent collaboration, agent teams, swarm orchestration, parallel task distribution, capability discovery, and quality gates on Claude Code, Codex, OpenClaw, and Cursor.
More from bybren-llc/safe-agentic-workflow
All 42 skills in this repoMulti-Agent Coordination Template
bybren-llc/safe-agentic-workflow
Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialist agents, managing blockers across agents…
API Route Patterns
bybren-llc/safe-agentic-workflow
API route implementation patterns with RLS, validation, and error handling. Use when creating API routes, implementing CRUD endpoints, adding server-side…
Technical Documentation Templates
bybren-llc/safe-agentic-workflow
Documentation templates for ADRs, runbooks, architecture docs, and knowledge transfer documents. Use when creating Architecture Decision Records, writing…
Deployment SOP Checklist
bybren-llc/safe-agentic-workflow
Deployment workflows, pre-deploy validation, smoke testing, and rollback procedures. Use when deploying to staging or production, running smoke tests…
Frontend Patterns Template
bybren-llc/safe-agentic-workflow
Frontend patterns for modern web frameworks, component libraries, auth flows, and analytics. Use when building UI components, creating pages, implementing…
Advanced Git Operations
bybren-llc/safe-agentic-workflow
Advanced git operations including rebase, bisect, cherry-pick, and conflict resolution. Use when rebasing feature branches, debugging with bisect…
Related
Categories
Questions about Team Coordination
What does Team Coordination do?
Agent Teams orchestration patterns for multi-agent SAFe workflows. Team Coordination is an agent skill from bybren-llc/safe-agentic-workflow. Agent Teams orchestration patterns for multi-agent SAFe workflows.
When should I use Team Coordination?
Team Coordination fits situations like: spawning agent teams; coordinating teammates; enforcing quality gates via task dependencies; orchestrating the 11-agent SAFe pipeline.
How do I install Team Coordination in Claude Code?
Run `npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a claude-code`. Or copy the skill folder (.agents/skills/team-coordination in bybren-llc/safe-agentic-workflow) into .claude/skills/team-coordination in your project. Claude Code loads it when a task matches its description.
How do I install Team Coordination in Codex?
Run `npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a codex`. Or copy the skill folder (.agents/skills/team-coordination in bybren-llc/safe-agentic-workflow) into .agents/skills/team-coordination in your project. Codex loads it when a task matches its description.
Can I use Team Coordination in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bybren-llc/safe-agentic-workflow --skill team-coordination -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/team-coordination, .gemini/skills/team-coordination, .github/skills/team-coordination and .opencode/skills/team-coordination in your project.
What does Team Coordination need to run?
SKILL.md names no scripts, command-line tools or credentials: Team Coordination is instructions for the agent only.
Does Team Coordination access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Team Coordination safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Team Coordination use?
Team Coordination is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Team Coordination use?
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Team Coordination?
Skills that share tags, products or a category with Team Coordination: OMA Multi-Agent Orchestrator (first-fluke/oh-my-agent, 1.3k stars), Swarm Parallel Dispatch (langchain-ai/langchain-skills, 1.3k stars), Nelson (Aspegio/nelson, 421 stars) and Cursor Orchestrate (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Team Coordination?
bybren-llc (a GitHub organization) maintains it in bybren-llc/safe-agentic-workflow, which has 423 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on July 20, 2026.
Source: bybren-llc/safe-agentic-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.