genie-orca-work

genie-orca-work is a skill for Codex from automagik-dev/genie. It costs 75 tokens per session (2,250 once invoked), scanned C, original, MIT.

A coordination skill for carrying out an approved work plan through Orca, with workers editing code in separate worktrees and reviewers checking the results. A worktree is an isolated copy of a Git working directory.

In plain words
What is it for?
It is for dispatching grouped tasks, supervising workers, rerunning validation, and moving work through review gates.
Why use it?
It organizes implementation, review, fixes, and status updates without letting the coordinator make unreviewed code changes.

Skill for Codex

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

Good fit It is for dispatching grouped tasks, supervising workers, rerunning validation, and moving work through review gates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/automagik-dev/genie/genie-orca-work
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 automagik-dev/genie --skill genie-orca-work
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie

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 genie-orca-work

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/automagik-dev/genie/genie-orca-work"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/genie-orca-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00075 $0.02250
Opus 5 $0.00037 $0.01125
Sonnet 5 $0.00015 $0.00450
Haiku 4.5 $0.00007 $0.00225

Measured 6d ago against content hash eeb6ce8ef024, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

genie-orca-work scanned grade C with 1 finding 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/migrate-to-linear.ts, scripts/retro-collect.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- After pruning dependencies, `rm -rf node_modules && bun install --frozen-lockfile` before trusting the gate — a stale `node_modules` hid a missing transitive dep that CI then caught.
skills/genie-orca-work/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

genie-orca:work — coordinator loop

Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.

Invariant. genie persists no lifecycle state. WISH.md is the only durable genie artifact. Orca owns the Run/Task/Dispatch state, Linear owns status, brain owns delegation preferences. If you find yourself writing a state file, stop.

You are the coordinator. A live LLM drives the loop below; Orca is the bus (it "never schedules or places workers"). Workers edit files; you never edit group files yourself. Reviewers are read-only; their worker_done reports findings and does not authorize edits.

Preconditions

  • WISH.md status APPROVED (human gate 1 passed), with a Dispatch plan table: id | depends_on | agent | model | effort | worktree | validation_cmd, and per-group Files / Do / Accept.
  • Orca up: ORCA status --json. Guide loaded this session: ORCA skills get orchestration (never run remembered flags).
  • Linear parent issue for the wish + one child per group (ids in the wish header). Create them with ORCA linear create … --parent <parent> --write-id <uuid5(slug/group)> — idempotent.

The loop (verbatim command shapes)

ORCA orchestration run-create --objective "<wish slug> (<LINEAR-ID>): <one line>" --json
# one task per group; spec = self-contained engineer brief (template below); deps = the wish's depends_on
ORCA orchestration task-create --spec "<brief>" [--deps '["task_…"]'] --json
# wave 1: every ready group, one supervised worker each, own child worktree
ORCA orchestration worker-start --task <task> --worktree new-child --name <slug>-g<n> \
     --base-branch <wish-branch> --agent <agent> --model <model> --effort <effort> --setup skip --json
# rolling wait — never sleep/poll; a timeout is a checkpoint, not a failure
ORCA orchestration check --wait --types worker_done,escalation,question --timeout-ms 900000 --json

Read the full file on GitHub · 95 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. 6d ago First seen · 95 lines · 75 tokens per session scan C eeb6ce8ef024

Subscribe to this mod's changes

genie-orca-work is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 2,250 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.