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 agentmods add skills/kriscard/skills/ideationnpx skills add kriscard/Skills --skill ideationgit clone --depth 1 https://github.com/kriscard/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/kriscard/skills/ideation)<a href="https://agentmods.dev/skills/kriscard/skills/ideation"><img src="https://agentmods.dev/badge/skills/kriscard/skills/ideation.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 | $0.00117 | $0.01706 |
| Opus 5 | $0.00059 | $0.00853 |
| Sonnet 5 | $0.00023 | $0.00341 |
| Haiku 4.5 | $0.00012 | $0.00171 |
Grade A, and why
ideation 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 5d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideation
Two modes. Detect which one the user needs.
Mode A — Conversation: Diverge, converge, stress-test, or spec in conversation. No files produced. Use when the user is exploring or analyzing.
Mode B — Pipeline: Full artifact generation (contract → PRD → spec). Use only when the user explicitly wants files such as a PRD, requirements, or implementation spec.
Boundary: use obsidian/ideas for merely capturing an idea, prototype when the user wants to build/scaffold/ship the MVP, and dev/spec when implementation scope is already chosen and needs a technical spec.
Completion Criteria
For conversation mode, finish only after one of these is true:
- Diverge: 8–10 options are produced and the user has a clear next choice.
- Converge: one recommendation is named with trade-offs and rejected options.
- Stress test: strongest version, riskiest assumption, failure modes, and next validation step are stated.
- Spec: problem, solution, success metric, v1 scope, and next steps are concrete.
For pipeline mode, finish only after written artifacts are created, approved gate-by-gate, and the final response lists generated file paths.
Mode A: Conversation
Thinking partner, not yes-machine. Challenge weak assumptions. Ask the uncomfortable question.
Detect the Conversation Move
Read the user's opening message and match to one move. Ask if genuinely unclear — but usually the framing tells you.
| Signal | Move |
|---|---|
| "generate ideas for...", "what are ways to..." | Diverge |
| "which of these should I...", "help me choose..." | Converge |
| "what could go wrong", "is this a good idea" | Stress test |
| "turn this into a plan", "what's the spec" | Spec |
Move: Diverge
Generate quantity first. Suspend judgment.
- Aim for 8–10 options before evaluating any.
- Include: obvious options, non-obvious options, one "that's crazy but...".
- Don't prematurely explain why each option would or wouldn't work.
- After generating: ask "Want me to narrow these down, or keep going?"
What ships with it
4 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.
- 5d ago First seen · 191 lines · 117 tokens per session scan A 9daa47ad7c99
ideation is a skill published in the GitHub repository kriscard/Skills (14 stars, last pushed 24d ago), licensed MIT. It adds 117 tokens to every session and 1,706 once invoked, about $0.0006 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
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
simple
Summarize short user notes into clear action items.
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…
aidlc-master
Runs the AWS AI-DLC (AI-Driven Development Life Cycle) methodology end to end: an adaptive three-phase workflow (Inception → Construction → Operations) with human approval gates, a full audit trail, and all artifacts in aidlc-docs/. Use when the user says "Using AI-DLC", "AI-DLC", "AIDLC", "aidlc-master", or asks for…
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…
astro-sites-manager
Comprehensive skill for building, migrating, and maintaining Astro v7 projects. Covers best practices from the official AGENTS.md, the v6→v7 migration path, validation of breaking/deprecated patterns, AI-enhanced dev server usage (background mode, JSON logging), advanced routing with src/fetch.ts, route caching…