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 SyloRei/claude-godmode --skill ideategit clone --depth 1 https://github.com/SyloRei/claude-godmodeWrote 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/sylorei/claude-godmode/ideate)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/ideate"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/ideate.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00078 | $0.02490 |
| Opus 5 | $0.00039 | $0.01245 |
| Sonnet 5 | $0.00016 | $0.00498 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
ideate 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideate
The pre-mission front door of the planning spine. Before /mission demands a decision — a feature name, a purpose, success criteria, constraints, a numbered roadmap — /ideate does the messy, generative work that precedes that decision: discuss candidate directions for the next mission, think each one through out loud, and converge on one concrete proposal. The proposal is written as a durable artifact that /mission then reads as its seed.
A charter is a contract, not a brainstorm. /ideate keeps the brainstorm out of /mission: it gives the user a real space to explore alternatives — with the reasoning preserved — and it gives /mission a synthesized starting point instead of a blank prompt. This is the spine's front door: /ideate → /mission → /brief N → /plan N → /build N → /verify N → /ship.
The artifact lives in the consumer's repo (the project you are helping build), never in the plugin source:
.planning/ideas/<slug>/IDEAS.md— one durable record per candidate feature.<slug>is the kebab-case proposed feature name.
This location is deliberately outside .planning/missions/: the prospective mission has no mission_id yet — /ideate runs before any mission is allocated for the idea. .planning/ideas/ is project-global scratch space at the .planning/ root, alongside PROJECT.md and STATE.md.
Pre-mission contract
/ideate is out-of-spine-order by design. It does not behave like the mission-scoped steps:
- Requires no active mission. It runs on a bare repo with no missions at all, before anything has been allocated.
- May run mid-mission. While a mission is active,
/ideateshapes the next mission without disturbing the current one. It does not read or rely on the active mission's state. - Does not start, switch, or mutate any mission. It allocates no
mission_id, resets no counter, writes no roadmap, touches no brief. It stops at a proposal — theIDEAS.mdartifact./missionremains the only skill that allocates amission_idand resets the work-unit counter. - No mission-flow state writes. Because it is pre-mission and out-of-order,
/ideatedoes not setactive_unitornext_commandinto a mission flow — that would corrupt an active mission's pointer. Any state write, if ever needed, goes only through thegodmode-statehelper; none is required. At most,/ideatesuggests/mission <name>as the next step in its output prose.
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 · 162 lines · 78 tokens per session scan A efbec23a447a
ideate is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 2,490 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
figma-verification
Extract Figma design specs before implementing UI components. Use depth 5, cache to disk, extract ALL properties, map to design system tokens.
interaction-design
Use when designing how a UI feels to use. Covers audience dimensions, discoverability, mode communication, keyboard-first UX, feedback timing, empty states, and information density. Includes WCAG 2.1 AA compliance audit. Companion to visual-design.
browser-testing
Adversarial browser testing. Use when testing UI behavior, verifying network requests, checking console errors, filling forms, or handling dialogs. The goal is finding bugs, not confirming happy paths.
debugging-protocol
Systematic protocol for diagnosing broken behavior and making recurrence structurally impossible. Schema mismatch causes 80% of bugs. Use when something isn't showing, isn't working, or is still broken after a fix attempt.
plan-mode
CEO and engineering review after spec-writing. Auto-selects weight class from the spec format (skip for task-mode, eng-only for routine, full CEO+eng for high-risk). Run /spec-writing first.
pr-review
Use when reviewing a PR or responding to review comments on your own PR. Detects authorship automatically and runs the correct mode. Never makes code changes when reviewing someone else's work.