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 danicat/speedgrapher --skill ideategit clone --depth 1 https://github.com/danicat/speedgrapherWrote 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/danicat/speedgrapher/ideate)<a href="https://agentmods.dev/skills/danicat/speedgrapher/ideate"><img src="https://agentmods.dev/badge/skills/danicat/speedgrapher/ideate/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/danicat/speedgrapher/ideate"><img src="https://agentmods.dev/badge/skills/danicat/speedgrapher/ideate.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 | $0.00104 | $0.02884 |
| Opus 5.5 | $0.00042 | $0.01154 |
| Sonnet 5.5 | $0.00021 | $0.00577 |
| Haiku 4.5 | $0.00010 | $0.00288 |
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 4d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideate: Socratic Discovery & Inverted-Pyramid Outlining
ideate unifies two foundational pre-writing disciplines: Socratic technical interviewing (extracting high-information-gain engineering reality before a single paragraph is drafted) and Inverted-Pyramid Information Architecture (ordering every document by descending reader value).
1. Mode Selection: Discovery Interview vs. Direct Structural Outlining
Choose your entry point based on how much raw material is already in context:
- Interactive Socratic Interview (Default for New Blog Posts & Articles):
- When the user wants to brainstorm a post or says "interview me about X", conduct a focused Socratic interview one question at a time to extract all 4 Pillars before generating the outline.
- Direct Inverted-Pyramid Outlining / Structural Refactoring:
- When the user already provides raw notes, code files, or an existing
README.md/SKILL.md/ draft to restructure, inspect the workspace artifacts directly and organize them into the target inverted-pyramid sequence.
- When the user already provides raw notes, code files, or an existing
2. Socratic Discovery: The 4 Pillars of Information Gain
Generic AI articles fail because they summarize public documentation and describe only the happy path. Your interview must extract four pillars of first-hand engineering experience:
| Pillar | What to Extract | Example Probing Question |
|---|---|---|
| 1. The Triggering Incident / Problem | The specific production alert, customer bug, latency ceiling, or developer friction that forced action. | "What was the exact failure metric or bottleneck that convinced you the existing implementation wouldn't hold up?" |
| 2. Failed Hypotheses & Dead Ends | The first one or two intuitive fixes that did not work, and the mechanism that broke them. | "Before you landed on the final design, what was your first instinct—and how did that attempt fail?" |
| 3. Concrete Artifacts | Verbatim error logs, stack traces, pprof profiles, minimal before/after diffs, benchmark tables, or architecture diagrams. |
"Do you have the panic stack trace, benchstat output, or minimal code diff we can anchor the lead section around?" |
| 4. Breakthrough & Engineering Trade-offs | The specific insight that solved the problem, the measurable outcome, and the new operational boundaries introduced. | "Once the fix went live, how did the metrics move—and under what conditions should another team avoid this approach?" |
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.
- 4d ago First seen · 175 lines · 104 tokens per session scan A 28ef4f9a7b3b
ideate is a skill published in the GitHub repository danicat/speedgrapher (51 stars, last pushed 4d ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,884 once invoked, about $0.0004 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 2026-10-17.
Other skills, from other repositories
astro
Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.
altorank
Run AltoRank through its hosted MCP server: readiness audits, Search Console, keyword research, and SEO drafts into a review queue.
mm-web-bridge
An idea partner for a developer who discusses plans, checks current information online, and prepares self-contained tasks for Claude Code running in Windows PowerShell. It is designed for Russian-language work and mentions Telegram bots, Python, SQLite, and Railway deployment.
mm-init-project
A project setup workflow that creates a shared project record in Markdown files, including a passport, dashboard, handoff notes, and instructions for Claude.ai. Obsidian is a note-taking app that can store these files as a connected project vault.
mm-save-session
An end-of-session recorder for Claude Code that saves the conversation summary and project state in Obsidian notes. Obsidian is a note-taking app that stores information as files.
mm-handoff
A skill that creates a compact handoff.md summary for starting a new Claude chat when the current chat is full. The file records recent work, current status, open questions, and selected project context.