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/heyparsadev/claude-idea-validatorWrote 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/heyparsadev/claude-idea-validator/idea-redteam)<a href="https://agentmods.dev/commands/heyparsadev/claude-idea-validator/idea-redteam"><img src="https://agentmods.dev/badge/commands/heyparsadev/claude-idea-validator/idea-redteam/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/commands/heyparsadev/claude-idea-validator/idea-redteam"><img src="https://agentmods.dev/badge/commands/heyparsadev/claude-idea-validator/idea-redteam.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 | $0.00015 | $0.00218 |
| Opus 5.5 | $0.00006 | $0.00087 |
| Sonnet 5.5 | $0.00003 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
idea-redteam 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 1mo 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.
What it actually says
Red-team this idea: $ARGUMENTS
Launch the idea-red-team agent with the hypothesis as its brief. If $ARGUMENTS names a venture in ventures/, read 00-idea-stage/01-hypothesis.md first and pass the current hypothesis version verbatim.
When the agent returns:
- Write the result to
ventures/<slug>/00-idea-stage/02-redteam.mdif a workspace exists. - Append every finding to
EVIDENCE.mdwith its grade and source, marked as challenging. - Present the ranked findings to the founder and ask them to concede or rebut each one — record which, with reasoning.
The gate: at least one finding the founder concedes is genuinely worrying. If nothing lands, the red team was too soft — run it again with a harder brief.
Respond in the founder's language.
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.
- 1mo ago First seen · 18 lines · 15 tokens per session scan A 46b2fcadfd9a
idea-redteam is a command published in the GitHub repository heyparsadev/claude-idea-validator (2 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 218 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.