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/duthaho/skillhub/ideatenpx skills add duthaho/skillhub --skill ideategit clone --depth 1 https://github.com/duthaho/skillhubWrote 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/duthaho/skillhub/ideate)<a href="https://agentmods.dev/skills/duthaho/skillhub/ideate"><img src="https://agentmods.dev/badge/skills/duthaho/skillhub/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 | $0.00213 | $0.01264 |
| Opus 5 | $0.00106 | $0.00632 |
| Sonnet 5 | $0.00043 | $0.00253 |
| Haiku 4.5 | $0.00021 | $0.00126 |
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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ideate — diverge before you converge
/ideate — generate ideas for THIS repo (reads its AGENTS.md/README)
/ideate <topic|problem> — generate ideas for an arbitrary problem, no repo needed
Answer one question: what could this become that isn't obvious yet — and which of those directions actually deserves effort? Both halves matter. A session that only sprays ideas is a whiteboard; one that judges before it has range is just the first idea wearing a verdict. The deliverable is a short list of directions each carrying its own reason to live or die.
The enemy the whole skill is built against is premature convergence — latching onto the first plausible idea and spending the session polishing it. Every step below exists to hold divergence open long enough to be worth converging on.
Step 0 — Frame the ground
You cannot diverge from nothing; fix a starting point first.
- With a repo (
/ideatealone): readAGENTS.md(the map skill writes it),README, and the top-reacted open issues. Distill the project's job in one sentence and its differentiation axis — the thing it does that alternatives don't, which every later verdict is judged against. - With a topic (
/ideate <problem>): restate the problem in one sentence and name the user and the constraint that hurts most. Missing pieces are assumptions — state them, don't invent facts. - Read
out/ideate/tracker.mdif it exists: ideas already generated, verdicts already made. A DROPped idea isn't re-raised unless something changed; repeat runs open with "Since last ideate" — what's new in the repo or problem since.
Completion criterion: job, user, and differentiation/constraint written down before any idea is generated.
Step 1 — Diverge (judgment forbidden here)
Generate ideas by working the lenses in
references/lenses.md — do not freehand a flat list,
which is how every session collapses into variations of one idea. Take each
lens in turn and force at least one idea from it, even a weak one; range
comes from the lenses being different, not from trying harder on one.
What ships with it
1 file 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.
- 3d ago First seen · 108 lines · 213 tokens per session scan A d65fcc7ec87e
ideate is a skill published in the GitHub repository duthaho/skillhub (9 stars, last pushed 10d ago), licensed MIT. It adds 213 tokens to every session and 1,264 once invoked, about $0.0011 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
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…