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 skills add automagik-dev/genie --skill genie-orca-wishgit clone --depth 1 https://github.com/automagik-dev/genieWrote 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.
[](https://agentmods.dev/skills/automagik-dev/genie/genie-orca-wish)<a href="https://agentmods.dev/skills/automagik-dev/genie/genie-orca-wish"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/genie-orca-wish/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.
<a href="https://agentmods.dev/skills/automagik-dev/genie/genie-orca-wish"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/genie-orca-wish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 3 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.00849 |
| Opus 5 | $0.00026 | $0.00425 |
| Sonnet 5 | $0.00010 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
genie-orca-wish 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
genie-orca:wish
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.
The wish is the only durable genie artifact and the instruction source for every worker. Write it with the most capable model you have; everything downstream gets cheaper because of it.
Before writing
- Scout first, opine second. Dispatch a read-only scout for exact
file:line, mechanisms, existing tests and the concrete fix per defect/feature. Commit it asSCOUT.mdnext to the wish — workers and reviewers read it, and it pins line numbers to a SHA. - Read the repo rules (
.claude/rules/*, CLAUDE.md) and the council/design that produced this wish. - Read the delegation preferences from brain (
brain_profile_gettier slots) — freeze them into the Dispatch plan; workers never consult brain.
Required shape
Header table: Status | Slug | Priority | Base (branch @ sha, gate state) | Target (PR → branch) | Ground truth (SCOUT.md) | Orchestration (Orca/Linear ids once created) | Approval.
Sections (the v5 validator still enforces these names): Summary · Scope (IN/OUT) · Problem (table: # / defect / symptom) · Decisions · Simplicity Case · Dependencies · Non-goals · Success Criteria · Execution Strategy (waves) · Execution Groups · Files to Create/Modify · QA Criteria · Assumptions / Risks · Review Results · Dispatch plan · Status log.
Per group (### Group n: Gn — title): Files (exact paths, the worker touches nothing else) · Do (imperative, decided — no "consider") · Accept (a command and an observable, never "works").
Dispatch plan table — the literal argument list:
| id | depends_on | agent | model | effort | worktree | validation_cmd |
|---|
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.
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.
- 7d ago First seen · 45 lines · 51 tokens per session scan A c3f903c419cc
genie-orca-wish is a skill published in the GitHub repository automagik-dev/genie (335 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 849 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.
Other skills, from other repositories
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
linear-graphql-skill
Operate Linear workspace issues, projects, and teams through Linear GraphQL API using UXC. Use when tasks require querying or creating issues, managing projects, or interacting with Linear workflow. Supports both Personal API Key and OAuth authentication.
speedrun
Interactive speedrun loop for small, low-risk changes. Delegates each request to a general sub-agent. Redirects larger work to /build-fast or /build.
phase-plan
Decompose a completed PRD or oversized requirements artifact into durable delivery phases.
{{BUCKET}}-management
Skill "{{BUCKET}}-management" from damusix/atomic-claude, covering purpose, doc shape and frontmatter contract.