wish

wish is a skill for Claude Code, Codex from automagik-dev/genie. It costs 22 tokens per session (2,214 once invoked), scanned A, original, MIT.

A planning procedure that turns an idea into a structured work plan called a wish. The plan records the project's scope, success conditions, and groups of work to be completed.

In plain words
What is it for?
Use it to define non-trivial features or changes, break them into execution groups, and record acceptance criteria in a WISH.md file.
Why use it?
It makes larger changes easier to understand and execute before coding begins. The written plan also gives other agents a shared description of the work.

Skill for Claude CodeCodex

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 skills/automagik-dev/genie/wish
Any agent
npx skills add automagik-dev/genie --skill wish
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie

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 wish

README.md
[![agentmods](https://agentmods.dev/badge/skills/automagik-dev/genie/wish.svg)](https://agentmods.dev/skills/automagik-dev/genie/wish)
Your own site
<a href="https://agentmods.dev/skills/automagik-dev/genie/wish"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/wish.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.02214
Opus 5 $0.00011 $0.01107
Sonnet 5 $0.00004 $0.00443
Haiku 4.5 $0.00002 $0.00221

Measured 6d ago against content hash 7b58f5de3012, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/design-review-evidence.mjs), 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.

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/wish/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wish — Plan Before You Build

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.

Convert a validated idea into an executable wish document at .genie/wishes/<slug>/WISH.md.

When to Use

  • Non-trivial work needs planning before implementation.
  • User wants to scope, decompose, or formalize a feature/change.
  • Prior brainstorm output exists and needs to become actionable.

Wish artifacts live in .genie/wishes/ in the shared worktree. Execution-group definitions go in WISH.md (git) so other agents and skills can read them; per-group execution state lives in the state DB via genie task (see the work skill for how groups are claimed and completed). When spawned as a native subagent, use the curated context from your dispatch prompt directly.

Before writing the wish, check the design exists and, when present, verify the review evidence with the helper shipped in this skill:

test -f .genie/brainstorms/<slug>/DESIGN.md
node "<wish-skill-dir>/references/design-review-evidence.mjs" verify ".genie/brainstorms/<slug>/DESIGN.md"
  • Present and verification exits 0: consume the reviewer-bound evidence and emit | **Design** | [DESIGN.md](../../brainstorms/<slug>/DESIGN.md) |.
  • Present but verification fails: stop and return to design review. Missing evidence, a non-SHIP verdict, or a content-digest mismatch cannot be waived; editing DESIGN.md invalidates its prior review. Never repair the failure with a locally recomputed digest — only a new design review may return the reviewed-sha256 passed to stamping.
  • Absent: emit | **Design** | _No brainstorm — direct wish_ | (no link) — valid for hotfixes, trivial changes, or plans obvious enough that a brainstorm adds no value. The linter (scripts/wishes-lint.ts) accepts the literal stub text; a bracket-link to a non-existent brainstorm file fails lint.

Read the full file on GitHub · 114 lines

Files

What ships with it

3 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 · 114 lines · 22 tokens per session scan A 7b58f5de3012

Subscribe to this mod's changes

wish is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 2,214 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.