agentmods.dev

OrchestrateKit Agent Planner

OrchestrateKit Agent Planner is a skill for Claude Code, Codex from orchestratemcp/OrchestrateKIT-MCP. It costs 50 tokens per session (583 once invoked), scanned A, original, MIT.

A planning guide for OrchestrateMCP, a system for designing multi-step AI-agent workflows. It helps define goals, permissions, human approval, monitoring, audit logs, and where results should go.

In plain words
What is it for?
Planning, reviewing, and handing off AI automations, tool workflows, and workflows that may write, publish, send messages, schedule tasks, or deploy changes.
Why use it?
It exposes safety and scope decisions before an agent workflow is built or handed off. It is intended as a reusable starting point when live planning tools are unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 14d ago A scan 50 tokens original MIT

Good fit Planning, reviewing, and handing off AI automations, tool workflows, and workflows that may write, publish, send messages, schedule tasks, or deploy changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner
View source ↗ orchestratemcp/OrchestrateKIT-MCP orchestratemcp.dev
Install

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.

Any agent
npx skills add orchestratemcp/OrchestrateKIT-MCP --skill orchestratekit-agent-planner
Clone the repo
git clone --depth 1 https://github.com/orchestratemcp/OrchestrateKIT-MCP

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for OrchestrateKit Agent Planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner/github.svg)](https://agentmods.dev/skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner)
Your own site
<a href="https://agentmods.dev/skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner"><img src="https://agentmods.dev/badge/skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for OrchestrateKit Agent Planner

Your own site · 80×15
<a href="https://agentmods.dev/skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner"><img src="https://agentmods.dev/badge/skills/orchestratemcp/orchestratekit-mcp/orchestratekit-agent-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 583 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00583
Opus 5 $0.00025 $0.00292
Sonnet 5 $0.00010 $0.00117
Haiku 4.5 $0.00005 $0.00058

Measured 9d ago against content hash d577728a0853, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

OrchestrateKit Agent Planner 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 9d 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.

distribution/claude-skill/orchestratekit-agent-planner/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OrchestrateKit Agent Planner

Use OrchestrateMCP as the source of truth when its MCP tools are connected. This Skill is a portable on-ramp and fallback, not a replacement for live registry matching.

First response

If the user has not supplied a concrete workflow goal, ask for the goal before planning. A goal is the thing they want the agent or automation to do.

Before planning, clarify any missing constraints that change safety:

  • Is the workflow read-only, or may it write, commit, publish, send, schedule, or deploy?
  • Will a human approve risky actions, or must it run unattended?
  • Is outbound email, Slack, publishing, customer communication, or production mutation allowed?
  • Where should monitoring, audit logs, and final output land?

When OrchestrateMCP tools are connected

  1. Call plan_workflow with the user's goal and the clarified constraints in plain English.
  2. Render summary_markdown verbatim, including the continuation menu.
  3. Explain unfamiliar or risky components with explain_component.
  4. If the user wants a known pattern, call get_playbook or read orchestratekit://playbooks/<playbook_id> when the ID is known.
  5. If the user wants implementation handoff, confirm scope and then call export_build_brief.
  6. Treat compose_workflow_route output as a draft candidate route until reviewed for untested edges and safety warnings.

Do not invent components, edges, registry counts, playbook statuses, or validation claims. Prefer live tool output over this Skill's static references whenever they differ.

When OrchestrateMCP tools are not connected

Use the references as a static planning aid:

  • Read references/playbooks.md to match the user's goal to a known pattern.
  • Read references/safety-checklist.md before recommending any write, send, publish, schedule, deploy, or loop.
  • Read references/setup.md when the user needs the hosted MCP connection.

Be explicit that offline Skill mode cannot score route confidence, inspect the latest registry graph, or export a deterministic Plan Passport. Recommend connecting the hosted MCP endpoint for those steps.

Read the full file on GitHub · 47 lines

Files

What ships with it

4 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.

Changes

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.

  1. 9d ago First seen · 47 lines · 50 tokens per session scan A d577728a0853

Subscribe to this mod's changes

OrchestrateKit Agent Planner is a skill published in the GitHub repository orchestratemcp/OrchestrateKIT-MCP (1 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 583 once invoked, about $0.0003 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.

Building agentsPlanningai-agentschatgptclaudecursordeveloper-toolsmcp
Related

Other skills, from other repositories

agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

yamadashy/repomix · 67 tokens

9router-stt

Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.

decolua/9router · 63 tokens

9router-web-fetch

Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.

decolua/9router · 67 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

requirements-authoring

To author, update, and validate functional/non-functional requirements as atomic units with user approval.

griddynamics/rosetta · 0 tokens