agent-team-orchestrator
Skill1 starsChanged 8 months agoMITView on GitHub
Coordinate multi-agent work in OpenCode using skills, Engram memory, and host-native delegation primitives instead of file-based mailboxes or lock files. Trigger: When work spans multiple areas, requires delegation, or the assistant must act as a director rather than a solo executor.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- InnovationMachineTeam/skillstheir own version, first seen Aug 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- InnovationMachineTeam/skills★ 1same 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.
In this repository10 other files it gives its agents.
- sdd-applySkill
- sdd-archiveSkill
- sdd-designSkill
- sdd-exploreSkill
- sdd-initSkill
- sdd-proposeSkill
- sdd-specSkill
- sdd-tasksSkill
- sdd-verifySkill
- skill-registrySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. About 0 are common, 8 are distinctive, and 12 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Do NOT force heavy orchestration for trivial factual answers.
- Very specific: line 25
Do NOT use tasks.json, mailbox folders, .lock files, or claim files as the primary coordination layer
- Very specific: line 26
Use host-native primitives: subagents, matching skills, slash commands, Engram, and TodoWrite when useful
- Distinctive: line 28
Do NOT parallelize overlapping paths
- Very specific: line 73
Every delegated worker MUST return valid JSON conforming to schemas/worker-output.schema.json.
- Distinctive: line 121
After reading sub-agent output, the orchestrator MUST reject:
- Distinctive: line 128
If rejected, log the error and optionally retry the sub-agent.
- Very specific: line 148
Use enter_plan_mode for structured planning before implementation
- Very specific: line 159
Windows (PowerShell): Use Start-Job + Wait-Job with codex.cmd
- Very specific: line 160
Linux/Mac (bash): Use & + wait with codex
- Very specific: line 195
Always use --ephemeral (no session persistence for sub-agents)
- Very specific: line 196
Always use --full-auto (no approval prompts)
- Very specific: line 197
Always use -o <file> (capture output to file)
- Very specific: line 198
Windows: Use codex.cmd (not codex.ps1), $env:TEMP for temp dir, Start-Job/Wait-Job for parallelism
- Very specific: line 199
Linux/Mac: Use -C "$(pwd)" (same working directory), /tmp/ for temp dir, &/wait for parallelism
- Very specific: line 200
Use praxisgenai-sub{N}.json naming convention (JSON output, not markdown)
- Distinctive: line 202
If a sub-agent fails, read its output for error info
- Distinctive: line 209
If you are running in an editor without native sub-agents:
- Distinctive: line 212
ALWAYS save results to Engram after each phase
- Distinctive: line 213
ALWAYS load prior artifacts from Engram before each phase
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
When to Use
- Requests that touch multiple files, modules, or architectural areas
- Work that benefits from exploration before implementation
- Multi-step execution that risks context bloat
- Any SDD workflow
Do NOT force heavy orchestration for trivial factual answers.
Hard Rules
- Do NOT use
tasks.json, mailbox folders,.lockfiles, or claim files as the primary coordination layer - Use host-native primitives: subagents, matching skills, slash commands, Engram, and
TodoWritewhen useful - Assign ownership by area, path, capability, or phase
- Do NOT parallelize overlapping paths
- Save meaningful discoveries, bug fixes, decisions, and conventions with
mem_save
Coordination Stack
Taskwhen you need bounded delegated workTodoWritewhen tracking adds clarityengramfor persistent state and recovery- SDD skills for substantial changes
explorefor investigation andgeneralfor implementation when those subagents are available
Scaling Rules
- Small task: one bounded delegation or one matching skill
- Medium task: explore -> implement -> verify
- Large task:
sdd-explore -> sdd-propose -> sdd-spec/design -> sdd-tasks -> sdd-apply -> sdd-verify -> sdd-archive
Ownership Model
Good boundaries:
src/auth/**docs/api/**verify regression coveragedesign state persistence
Bad boundaries:
- "whatever is free"
- "take backend maybe"
- lock-file claims
Memory Rules
Save important outcomes with mem_save using:
titletypeprojectcontentwithWhat,Why,Where, andLearned
For evolving topics, reuse topic_key.
Sub-Agent Output Contract
Every delegated worker MUST return valid JSON conforming to schemas/worker-output.schema.json.
Schema reference: schemas/worker-output.schema.json (repo) or ~/.codex/schemas/worker-output.schema.json (installed).
Enforcement by editor:
- Codex: Uses
codex exec --output-schema <path>to enforce the schema at runtime. - OpenCode and Gemini: Follow the same contract via prompt instruction (no native schema enforcement).
Status Values
| Status | Meaning |
success | Task completed fully. verification.performed MUST be non-empty. |
partial | Task partially done. Some work completed, but not everything. |
blocked | Cannot proceed. Explain why in risks. |
Example Output
{
"contract_version": "1.0",
"worker_id": "sub1",
"task_id": "explore-auth",
"status": "success",
"executive_summary": "Traced the full authentication flow...",
"ownership": {
"area": "src/auth/**",
"touched_paths": ["src/auth/login.ts", "src/auth/session.ts"],
"untouched_paths": ["src/payments/**"]
},
"artifacts": { "created": [], "updated": [], "references": ["docs/auth-flow.md"] },
"findings": ["Sessions persist in localStorage — vulnerable to XSS"],
"decisions": ["Focus on token lifecycle before session storage"],
"changes": [],
"verification": {
"performed": ["Code reading", "Flow tracing"],
"not_performed": ["Unit tests", "E2E flow"]
},
"risks": ["The interceptor is a global singleton — changes affect ALL API calls"],
"next_recommended": ["Implement refresh token rotation"],
"memory_saved": []
}See schemas/worker-output.example.json for a complete example.
Orchestrator Validation Rules
After reading sub-agent output, the orchestrator MUST reject:
- Invalid JSON (parse error)
- Missing required fields (any field from the schema's
requiredlist) - Invented status (status not in
["success", "partial", "blocked"]) - Paths outside ownership (paths in
touched_pathsoutside declaredownership.area) - Success without evidence (status
"success"with emptyverification.performed— no evidence = no trust)
If rejected, log the error and optionally retry the sub-agent.
Delegation Model per Editor
The orchestrator adapts its behavior based on the runtime's actual capabilities:
Claude Code (native — no orchestrator needed)
- Uses built-in
Agenttool with typed sub-agents (Explore, Plan, general) - Full context isolation per sub-agent
- This skill is NOT needed in Claude Code
OpenCode (full sub-agent support)
- Uses
subtask: truein command definitions to spawn isolated agent contexts - Each SDD phase runs as a dedicated agent with its own system prompt
- The orchestrator delegates via slash commands:
/sdd-explore,/sdd-apply, etc. - Results flow back through the conversation
Gemini CLI (sub-agent via tools)
- Uses
SubagentTool— sub-agents are exposed as callable tools - Skills can be loaded dynamically with
activate_skill - Use
enter_plan_modefor structured planning before implementation - The orchestrator invokes skills directly, each running in isolated context
Codex (Simulated Sub-Agents via codex exec)
- Codex has NO native sub-agents, but can SIMULATE them using
codex execin background - The main Codex spawns up to 4 parallel
codex execprocesses - Each sub-process writes its result to a temp file via
-oflag - Main Codex reads all output files and synthesizes
How to delegate in Codex:
Windows (PowerShell): Use Start-Job + Wait-Job with codex.cmd
Linux/Mac (bash): Use & + wait with codex
Important: codex.ps1 may be blocked by execution policy. Always use codex.cmd on Windows.
# Windows (PowerShell) — Launch up to 4 sub-agents in parallel
$schema = Join-Path $PSScriptRoot 'schemas' 'worker-output.schema.json'
# Or use the installed path:
# $schema = "$HOME\.codex\schemas\worker-output.schema.json"
$jobs = @()
$jobs += Start-Job { & 'codex.cmd' exec --full-auto --ephemeral --output-schema $using:schema -o "$env:TEMP\praxisgenai-sub1.json" 'PROMPT FOR TASK 1' }
$jobs += Start-Job { & 'codex.cmd' exec --full-auto --ephemeral --output-schema $using:schema -o "$env:TEMP\praxisgenai-sub2.json" 'PROMPT FOR TASK 2' }
$jobs | Wait-Job
$result1 = Get-Content "$env:TEMP\praxisgenai-sub1.json" | ConvertFrom-Json
$result2 = Get-Content "$env:TEMP\praxisgenai-sub2.json" | ConvertFrom-Json
if ($result1.status -notin @('success','partial','blocked')) { Write-Error "Invalid status from sub1" }
if ($result2.status -notin @('success','partial','blocked')) { Write-Error "Invalid status from sub2" }
Remove-Item "$env:TEMP\praxisgenai-sub*.json" -ErrorAction SilentlyContinue# Linux/Mac (bash) — Launch up to 4 sub-agents in parallel
SCHEMA="$HOME/.codex/schemas/worker-output.schema.json"
codex exec --full-auto --ephemeral --output-schema "$SCHEMA" -C "$(pwd)" -o /tmp/praxisgenai-sub1.json "PROMPT FOR TASK 1" &
codex exec --full-auto --ephemeral --output-schema "$SCHEMA" -C "$(pwd)" -o /tmp/praxisgenai-sub2.json "PROMPT FOR TASK 2" &
wait
# Validate with jq
echo "$(cat /tmp/praxisgenai-sub1.json)" | jq -e '.status' > /dev/null || echo "INVALID sub1"
echo "$(cat /tmp/praxisgenai-sub2.json)" | jq -e '.status' > /dev/null || echo "INVALID sub2"
rm /tmp/praxisgenai-sub*.jsonRules:
- Maximum 4 parallel sub-agents (to avoid saturating the machine)
- Always use
--ephemeral(no session persistence for sub-agents) - Always use
--full-auto(no approval prompts) - Always use
-o <file>(capture output to file) - Windows: Use
codex.cmd(notcodex.ps1),$env:TEMPfor temp dir,Start-Job/Wait-Jobfor parallelism - Linux/Mac: Use
-C "$(pwd)"(same working directory),/tmp/for temp dir,&/waitfor parallelism - Use
praxisgenai-sub{N}.jsonnaming convention (JSON output, not markdown) - Clean up temp files after reading
- If a sub-agent fails, read its output for error info
For sequential phases (when parallelism doesn't help):
- Still use
codex execbut run one at a time - Save results to Engram between phases for cross-session continuity
Detection Rule
If you are running in an editor without native sub-agents:
- In Codex: use
codex execto simulate sub-agents (see Codex section above) - In other editors without sub-agents: execute phases inline sequentially
- ALWAYS save results to Engram after each phase
- ALWAYS load prior artifacts from Engram before each phase
Commands
/orch-help
/orch-status
/orch-doctor
/orch-init
/skill-registry
/sdd-init
/sdd-new change-name
/sdd-apply change-nameDoes 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.

