orch-planner

orch-planner is an agent for coding agents from geekatron/jerry. It costs 22 tokens per session (3,443 once invoked), scanned A, original, no licence file.

A planning assistant for designing workflows that use multiple agents and defining how those workflows store their state.

In plain words
What is it for?
It helps design multi-agent workflows, plan pipeline structures, and define the data fields used to track workflow state.
Why use it?
It helps break complex work into coordinated steps so different agents can contribute in an organized way.

Agent

Part of the jerry plugin — 13 skills, 2 commands, 39 agents, 6 hooks shipped together

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.

agentmods
npx agentmods add agents/geekatron/jerry/orch-planner
Clone the repo
git clone --depth 1 https://github.com/geekatron/jerry

Or install jerry, the plugin that ships this one along with the rest of its 13 skills, 2 commands, 39 agents, 6 hooks.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00022 $0.03443
Opus 5 $0.00011 $0.01722
Sonnet 5 $0.00004 $0.00689
Haiku 4.5 $0.00002 $0.00344

Measured 3d ago against content hash 2f5625736044, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orch-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 3d 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.

skills/orchestration/agents/orch-planner.md · 392 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 3d ago First seen · 392 lines · 22 tokens per session scan A 2f5625736044

Subscribe to this mod's changes

orch-planner is an agent published in the GitHub repository geekatron/jerry (31 stars, last pushed yesterday), with no licence file. It adds 22 tokens to every session and 3,443 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

Azure Logic Apps Expert Mode

Expert guidance for Azure Logic Apps development focusing on workflow design, integration patterns, and JSON-based Workflow Definition Language.

github/awesome-copilot · 28 tokens

workflow-literal

Pipeline step processor for inline prompt literals in workflow DSL. Executes user-provided instructions against pipeline context.

kangig94/coral · 24 tokens

project-manager

Use PROACTIVELY at the start of each sprint or product cycle to align technical work with business objectives. This agent specializes exclusively in product strategy and prioritization - creating roadmaps, defining acceptance criteria, analyzing market needs, and maximizing ROI. Automatically generates PRDs from…

schuettc/claude-code-plugins · 77 tokens

design-auditor

Reads a user's agent artifact (skill, agent definition, plugin, hooks, or multi-agent workflow) strictly read-only and consults the published agentic-atlas corpus, returning either a cited audit of the artifact against the patterns or a cited edit plan for applying one named pattern. Two modes selected by the dispatch…

aj604/agentic-atlas-plugin · 92 tokens

extraction-worker

Per-patient clinical note extraction worker. Reads ontology definitions and extracts structured data from clinical text using domain-group-based extraction. Writes structured JSON result to a specified output path. Spawned by the extract-notes skill -- do not invoke directly.

kenlkehl/onc-data-wrangler-plugin · 54 tokens

tech

Technical Architect agent for spec workflow. Reviews PRD for technical clarity issues, then designs HOW to build the system. Identifies unclear requirements that could cause implementation confusion. Defines modules, APIs, data models, tech stack decisions, and architectural constraints. Third analyst in serial…

mylukin/agent-foreman · 68 tokens