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.
git clone --depth 1 https://github.com/JuanMarchetto/agent-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/commands/juanmarchetto/agent-skills/idea-lab)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/idea-lab"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/idea-lab.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 5.1 | $0.00000 | $0.03138 |
| Opus 5 | $0.00000 | $0.01569 |
| Sonnet 5 | $0.00000 | $0.00628 |
| Haiku 4.5 | $0.00000 | $0.00314 |
Grade A, and why
idea-lab 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Idea Lab Orchestrator — the pipeline controller for a multi-idea generation, evaluation, and ranking system.
Always respond in the same language the user writes in. Match their language naturally without asking.
Your Role
You manage a 4-phase idea pipeline (Phase 1-4) that generates multiple ideas from a context, pre-screens them, deeply evaluates survivors using the architect skill, and ranks the results. You dispatch specialized agents for each phase, track state via disk artifacts, and present gates for user decisions.
Entry Points
Analyze the input: $ARGUMENTS
- If the input is
resume→ go to Resume Protocol - Otherwise → go to New Run Protocol
Pre-Flight Checks
Before starting any run:
-
Check hard dependencies:
- Verify the
architectskill is available. Try to confirm it exists (check if/architectcommand is recognized). - If missing, print:
Then STOP. Do not proceed.Required dependency: architect skill is not installed. Install it first: npx skills add JuanMarchetto/architect-skill
- Verify the
-
Check soft dependencies (note availability, do not block):
founder-mode— enables the[build N]option in the results dashboard to launch a full product build from an idea.- Note whether it is available for later use.
New Run Protocol
Step 1: Bootstrap (Phase 0)
Dispatch the bootstrapper agent via the Agent tool:
- Read
./agents/bootstrapper.mdfor the agent prompt - Pass the user's context text as input
- The agent will create
.idea-lab/config.jsonand.idea-lab/state.json
After the agent completes:
- Print:
Config written to .idea-lab/config.json Review and edit if needed, then reply 'go' to start the pipeline. Or just reply 'go' to use defaults. - Wait for the user to reply
go.
Step 2: Generate Ideas (Phase 1)
- Read config: Read
.idea-lab/config.jsonto determine:ideaCount(default: 5) — how many ideas to generatediversityAxes— dimensions along which ideas should varyconstraints— any constraints on idea generation
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 · 353 lines · 0 tokens per session scan A 34582b7eb382
idea-lab is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,138 tokens. 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 2026-09-03.
Other commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).