orrery-dispatch

orrery-dispatch is a skill for Codex from ItIsMixian/Orrery. It costs 63 tokens per session (619 once invoked), scanned A, original, MIT.

A task handoff tool for projects that use Orrery’s documentation system, where committed decisions and plans define the work.

In plain words
What is it for?
It helps start, split, assign, or materially change tasks while recording the required decisions, implementation plans, and validation steps.
Why use it?
It keeps task references linked to approved requirements instead of copying them into a second, potentially outdated document.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit It helps start, split, assign, or materially change tasks while recording the required decisions, implementation plans, and validation steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itismixian/orrery/orrery-dispatch
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 ItIsMixian/Orrery --skill orrery-dispatch
Clone the repo
git clone --depth 1 https://github.com/ItIsMixian/Orrery

Made for: 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 orrery-dispatch

README.md
[![agentmods](https://agentmods.dev/badge/skills/itismixian/orrery/orrery-dispatch/github.svg)](https://agentmods.dev/skills/itismixian/orrery/orrery-dispatch)
Your own site
<a href="https://agentmods.dev/skills/itismixian/orrery/orrery-dispatch"><img src="https://agentmods.dev/badge/skills/itismixian/orrery/orrery-dispatch/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 orrery-dispatch

Your own site · 80×15
<a href="https://agentmods.dev/skills/itismixian/orrery/orrery-dispatch"><img src="https://agentmods.dev/badge/skills/itismixian/orrery/orrery-dispatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 619 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00063 $0.00619
Opus 5 $0.00032 $0.00309
Sonnet 5 $0.00013 $0.00124
Haiku 4.5 $0.00006 $0.00062

Measured 6d ago against content hash ce5589cf5ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orrery-dispatch 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 6d 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/orrery-dispatch/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orrery Dispatch

Create a task reference, not a second copy of its requirements.

Dispatch

  1. Read the target repository's AGENTS.md and the authority sources it requires. If the authority chain is absent or not integrated, report that state instead of inventing project facts.
  2. Require explicit user intent before creating a new task. Discussion, approval of a design direction, or “consider this later” does not authorize task creation.
  3. For a new task, write the effective ADR and Approved Design when required, plus an Implementation Plan and Pending Validation. For a material mid-flight change, send only an immediate stop instruction, then write a dated Plan amendment and update Pending Validation. For a new decision outside the explicitly identified unique integration worktree, use a stable PO-DEC-<task-id>-<slug> proposal under docs/decisions/proposals/; do not allocate a numeric ADR. A branch name or locally observed “next number” does not grant integrator authority. The integrator allocates and relinks the next free numeric ADR against the current integration index.
  4. Commit the authority-only change before task creation or resumption. Call this commit the 任务说明版本 in user-facing text; keep its full Git commit SHA in technical details.
  5. Create or continue the task using the host's task tool when available. Preserve the target project's worktree, model and reasoning conventions.
  6. Send only the task identity, code base when different, task-description version, exact authority paths, execution configuration and hard safety boundary. Do not repeat the requirements in the task message.
  7. Require the implementation Agent to read the exact committed sources, preserve dirty work, acknowledge the source version and register or refresh its Git-private scope before first or resumed product writes.
  8. Do not poll, wait on, or repeatedly read the task unless the user explicitly asks for monitoring.

If the host cannot create or message tasks, return the compact reference message for the user to send; do not invent a task or claim dispatch succeeded.

Read the full file on GitHub · 45 lines

Files

What ships with it

1 file 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. 6d ago First seen · 45 lines · 63 tokens per session scan A ce5589cf5ae7

Subscribe to this mod's changes

orrery-dispatch is a skill published in the GitHub repository ItIsMixian/Orrery (45 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 619 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 2026-09-03.

Related

Other skills, from other repositories