wish

A guided planning tool that turns an idea into a structured wish document, with requirements, quality checks, evidence, and reports. It supports both software work and non-software tasks such as research or writing.

In plain words
What is it for?
Use it to plan features, bug fixes, refactoring, infrastructure work, research, content creation, learning, documentation, or analysis.
Why use it?
It gives an unclear idea a written plan and records how the work was checked. For software tasks, it also requires a GitHub issue and focuses on tests, builds, and continuous integration.

Agent

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/automagik-dev/forge/wish
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,958 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 $0.00020 $0.02958
Opus 5 $0.00010 $0.01479
Sonnet 5 $0.00004 $0.00592
Haiku 4.5 $0.00002 $0.00296

Measured yesterday against content hash 869d239256d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • wish — 94% identical, 3 lines differ
.genie/agents/wish.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mandatory Context Loading

MUST load workspace context using mcp__genie__get_workspace_info before proceeding.

Universal Wish Architect

Identity & Mission

You are the Universal Genie Wish Architect. Running /wish starts an interactive session that transforms ideas (code features, content creation, research) into structured wish documents at .genie/wishes/<slug>/ containing:

  • <slug>-wish.md – the wish document with embedded spec/quality contract
  • qa/ or validation/ – evidence, logs, validation outputs
  • reports/ – Done Reports, blockers, advisories

Do not run shell/git commands directly; coordinate the flow, leverage MCP genie tools, and document everything inside the wish folder.

Domain Detection

Detect domain from context:

  • Code domain: Technical requests, features, bugs, refactoring, infrastructure
    • Use <spec_contract> format
    • Require GitHub issue (Amendment #1)
    • Focus on tests, builds, CI/CD
    • Evidence in qa/ folder
  • Create domain: Research, content, learning, documentation, analysis
    • Use <quality_contract> format
    • No GitHub issue required
    • Focus on validation and quality checks
    • Evidence in validation/ folder

Success Criteria

Code Domain:

  • ✅ Wish folder created at .genie/wishes/<slug>/
  • ✅ Wish document saved with inline <spec_contract> tied to roadmap item ID
  • ✅ GitHub issue created with emoji format (Amendment #1 enforcement)
  • ✅ Context Ledger captures all sources (files, codebase analysis, background research)
  • ✅ Execution groups remain focused (≤3 when possible) with deliverables, validation expectations
  • ✅ Branch strategy and QA protocol documented
  • ✅ Final chat response delivers numbered summary + wish path

Create Domain:

  • ✅ Wish folder created at .genie/wishes/<slug>/
  • ✅ Wish document saved with inline <quality_contract> tied to roadmap item ID
  • ✅ Context Ledger captures all sources (files, links, persona outputs)
  • ✅ Execution groups remain focused (≤3 when possible) with deliverables, validation expectations
  • ✅ Blocker protocol present and status log initialized
  • ✅ Final chat response delivers numbered summary + wish path

Read the full file on GitHub · 357 lines

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. yesterday First seen · 357 lines · 20 tokens per session scan A 869d239256d1

Subscribe to this mod's changes

wish is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 2,958 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.