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 ckorhonen/claude-skills --skill idea-mdgit clone --depth 1 https://github.com/ckorhonen/claude-skillsWrote 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/ckorhonen/claude-skills/idea-md)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/idea-md"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/idea-md/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/ckorhonen/claude-skills/idea-md"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/idea-md.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 | $0.00082 | $0.00926 |
| Opus 5 | $0.00041 | $0.00463 |
| Sonnet 5 | $0.00016 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
idea-md 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea.md
Overview
Create a strong Idea.md when the user has an early concept but not yet a full PRD. Treat it as the bridge between raw brainstorming and formal product requirements.
An Idea.md is not universal. If the repo already has a local convention, follow it. If not, default to the house definition in references/what-is-idea-md.md: a concise, structured concept brief that captures the problem, user, solution, repo fit, risks, and next validation steps.
Announce at start: I'm using the idea-md skill to create or refine the idea file.
Inputs to Gather
Pull from the richest available sources, in this order:
- Existing
Idea.md/IDEA.md/ related drafts - Current repo context:
README, specs, roadmap docs, issues, package structure, notable constraints - Conversation history and user-provided notes
- Adjacent artifacts such as PRDs, design docs, or research notes
If a repo exists, inspect it before writing. Do not invent technical context that could be learned from the codebase or docs.
Workflow
1. Determine the mode
Pick one:
- New idea file: no existing idea doc, user wants one created
- Expansion: user has a rough draft and wants it expanded
- Rewrite: user wants a cleaner, more structured version of an existing idea file
2. Infer the right format
- If the repo already uses an
Idea.mdconvention, preserve it. - If the workflow expects
Idea.mdas an upstream planning artifact, keep it structured and concise. - If the request is just idea capture, it can be lighter, but still make it legible to someone other than the original author.
Use references/idea-template.md when no local template exists.
3. Synthesize, do not merely transcribe
Turn rough notes into a coherent narrative:
- sharpen the core thesis
- remove repetition
- surface implicit assumptions
- separate what is known from what is speculative
- preserve genuinely distinctive phrasing or insights from the user
4. Ground it in reality
What ships with it
2 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.
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.
- 11d ago First seen · 116 lines · 82 tokens per session scan A e9bcb741c9ff
idea-md is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 926 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 2026-08-30.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.