Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/everyone-needs-a-copilot/claude-copilot/orchestratenpx skills add Everyone-Needs-A-Copilot/claude-copilot --skill orchestrategit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/orchestrate)<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/orchestrate"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/orchestrate.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00396 |
| Opus 5 | $0.00021 | $0.00198 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
orchestrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Orchestrate
Coordinate parallel work in a Codex-native way.
Boundary
Codex Copilot does not auto-spawn workers unless the user explicitly asks for delegation or parallel execution.
Workflow
- Use
tato create a PRD, task breakdown, streams, dependencies, and file ownership. - Validate stream dependencies and file overlap with
scripts/orchestrate-validate.pybefore any parallel work begins. - Use git worktrees only after confirming the branch/worktree plan with the user.
- Spawn Codex subagents only when explicitly requested.
- Keep write scopes disjoint and route each implementation stream through
qa. - Treat merge, cleanup, and removal operations as separate actions requiring explicit current approval when destructive.
- For a user-requested cost-capped non-interactive worker, pass
--max-budget-usdthroughtc worker; do not imply that stored metadata enforces a cap unless the installedtccontract says so.
Stream Metadata
Each stream should declare:
{
"streamId": "Stream-A",
"streamName": "Foundation",
"files": ["src/example.ts"],
"streamDependencies": [],
"streamPaths": ["src/example/**"],
"streamTokenBudget": 2500
}
Launch Template
When the user explicitly approves delegation, spawn each stream with:
- specialist role and skill
- task id and stream id
- owned files or path globs
- forbidden paths
- expected work product and QA route
Output
- stream plan
- dependency graph
- file ownership map
- launch instructions or local execution plan
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 57 lines · 42 tokens per session scan A 8c26c9ae6408
orchestrate is a skill published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 396 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
cadence-first
Meta-orchestrator: assigns skill-chain cadence per block (Tier 1/2/3) via Q1-Q6 rules. Reads target taskblocks + task.md, writes cadence-decisions-{R}.md artifact. Standalone (executor invokes) or Batch (generator hand-off). Use when: deciding cadence for a batch of blocks, generator hand-off from decomposition skills.
ship-first
Final task completion protocol: report → user-note → deploy → smoke test → close? → guide? → routing.db → propagate → STATUS → sessions. Invoked from fast-track and pipeline flows after task execution, not directly by the user. Use when: invoked after the execute step of a fast-track or pipeline task.
ui-ai-first
Final audit of a large task before closure — finds which operations are available only via code / curl / SQL and decides per each: automate with a skill or AI agent (A) or create a UI task (B). Protects against invisible usability debt. Walks through each implemented block: reads task.md + reports + guides + code →…
decision-first
Makes an architectural / project / scope decision using a 5-part model INSTEAD of asking the user. Structure: 🎯 Decision / Why / 🛡 Security / 📈 Scalability / Alternatives / Plain-language analogy. 1 question = 1 atomic artifact. Use when: the agent is about to ask an architectural / scope question…
library-first
Mandatory protocol before executing any fast-track task. Analyzes the task, builds a table: what we do / where it comes from / how many lines of code. Principle: maximum reuse of existing libraries and components, minimum new code. Waits for explicit user approval — does nothing until confirmed. Use when: fast-track…
fixture-new
Creates a parity fixture — the frozen scenario plus the contract its output must satisfy. Asks which skill and case, what shape the run must produce, and writes input.md and expect.yml. Ends by proving the new fixture actually fails on an empty directory. A fixture that passes when nothing ran is worse than no…