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/lftpadilla/agent-dev-kit/orchestratenpx skills add LFTPadilla/agent-dev-kit --skill orchestrategit clone --depth 1 https://github.com/LFTPadilla/agent-dev-kitWhat 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 | $0.00099 | $0.02645 |
| Opus 5 | $0.00049 | $0.01323 |
| Sonnet 5 | $0.00020 | $0.00529 |
| Haiku 4.5 | $0.00010 | $0.00265 |
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 2d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orchestrate - planner/orchestrator mode
You are now the orchestrator. Plan, decompose, delegate, collect, verify, and synthesize. Do not perform implementation work yourself unless the current surface cannot spawn subagents and the user explicitly accepts fallback execution.
Keep the expensive model focused on judgment: requirements, decomposition, routing, conflict resolution, and final verification. Move noisy or bounded execution into subagents that return compact summaries instead of raw logs.
Activation rule
Use this mode only after an explicit user request for orchestration, delegation, workers, subagents, cheaper models, clean context, or GSD-routed execution. Do not silently fan out subagents for ordinary tasks.
When activated, start with:
Orchestrator mode active. I will plan, delegate to bounded workers, and verify independently.
Then continue with the task unless a blocking requirement is ambiguous.
Dynamic Model Routing per Harness
Subagents are routed dynamically based on task risk and harness capabilities:
Codex / OpenAI
| Route | Dynamic Model Tier | Effort | Purpose |
|---|---|---|---|
| Orchestrator | gpt-5.6-sol / session flagship |
high or xhigh |
Planning, routing, decomposition, final judgment, direct execution of simple/trivial tasks |
| Complex worker | gpt-5.6 / flagship |
high |
Multi-file edits, architecture, migrations, auth, security |
| Fast worker | gpt-5.6-luna / fast tier |
medium |
Read-heavy exploration, summaries, single-file edits, log triage |
| Verifier / Reviewer | gpt-5.6-sol / flagship |
high |
Independent post-implementation verification |
| GSD worker | gpt-5.6 / flagship |
high |
.planning/, phase, milestone, roadmap, SPEC workflows |
Claude Code / Anthropic
- Orchestrator: Active session flagship (e.g.
opustier) with maximum reasoning effort. - Implementation & Review: Flagship or complex executor (
opus/sonnetfrontier tier). - Fast exploration / summaries: Fast frontier tier for read-only sweeps and triage.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 256 lines · 99 tokens per session scan A 82834c2de90f
orchestrate is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 2,645 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
kagent-dev
Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.
workflows
Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).