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 skillmds/skillmd --skill idea-osgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/idea-os)<a href="https://agentmods.dev/skills/skillmds/skillmd/idea-os"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/idea-os/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/skillmds/skillmd/idea-os"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/idea-os.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.01385 |
| Opus 5.5 | $0.00024 | $0.00554 |
| Sonnet 5.5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
idea-os 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
idea-os
An operating system for turning a raw idea into a build-ready plan. Takes a rough problem statement and produces four files: clarifying questions, deep research, a PRD, and a phased execution plan with platform/stack picks, a user-journey diagram, and kill criteria.
Overview
idea-os is a 5-phase sequential pipeline where each phase's output feeds the next — research shapes the PRD, PRD shapes the plan, plan's kill criteria tie back to research insights. Unlike single-command PRD generators, idea-os refuses to write a PRD until research is done, and refuses to write a plan until the PRD is stable. Depth and vocabulary adapt to a two-axis classification (complexity × builder sophistication) so a first-time builder isn't drowning in jargon and a founder gets full rigor.
Source: https://github.com/Slashworks-biz/idea-os — full skill, 11 reference files, 4 asset templates, and a 590-line worked example.
When to Use
- Use when a user shares a raw product idea or problem statement and wants a structured pipeline from clarifying questions through deep research, PRD, and a phased execution plan.
- Use when the user says "I have an idea for…", "help me build X", "validate and plan this concept", or "what should I build?" — and wants files they can take forward, not a one-shot answer.
- Use when a non-technical founder, PM, or hobbyist needs structure to bridge the gap between "idea" and "Monday morning's build queue".
- Do not use for quick sanity-check feedback on a half-formed idea (use
idea-refineinstead) or for editing an existing PRD (useproduct-managementinstead).
How It Works
Phase 1 — Triage
Classify the idea on two axes before anything else. Depth of research/PRD/plan and question count scale with complexity; vocabulary scales with sophistication.
- Idea tier (T1/T2/T3) — T1 = weekend utility, T2 = SaaS MVP or AI wrapper, T3 = marketplace / B2B SaaS / regulated.
- Sophistication (S1/S2/S3) — S1 = non-technical, no framework names; S2 = hobbyist, introduce frameworks with definitions; S3 = founder/senior PM, full vocabulary.
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.
- 1mo ago First seen · 90 lines · 60 tokens per session scan A 5b1a2081786a
idea-os is a skill published in the GitHub repository skillmds/skillmd (143 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 1,385 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
idea-os compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| idea-osskillmds/skillmd | Skill | 143 | 4d ago | MIT | A | 60 | Claude Code |
| ai-prd-generatorlaymom/ai-prd-generator | Skill | 1 | 22d ago | MIT | A | 156 | Claude Code, Codex |
| prd-taskmasteranombyte93/prd-taskmaster | Skill | 608 | 3d ago | MIT | A | 93 | Claude Code |
| handoffanombyte93/prd-taskmaster | Skill | 608 | 3d ago | MIT | A | 158 | Claude Code |
| generateanombyte93/prd-taskmaster | Skill | 608 | 3d ago | MIT | A | 91 | Claude Code |
| discoveranombyte93/prd-taskmaster | Skill | 608 | 3d ago | MIT | A | 92 | Claude Code |
| execute-fleetanombyte93/prd-taskmaster | Skill | 608 | 3d ago | MIT | A | 52 | Claude Code |