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 commands/heyparsadev/claude-idea-validator/idea-gategit 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-gate)<a href="https://agentmods.dev/commands/heyparsadev/claude-idea-validator/idea-gate"><img src="https://agentmods.dev/badge/commands/heyparsadev/claude-idea-validator/idea-gate.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 | $0.00015 | $0.00301 |
| Opus 5 | $0.00008 | $0.00151 |
| Sonnet 5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
idea-gate 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 6d 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
Score the Idea-stage exit gate for: $ARGUMENTS
Invoke founder-playbook:idea-stage and run step 10 only. Read references/evidence-ledger.md for the gate arithmetic.
- Read
ventures/<slug>/00-idea-stage/EVIDENCE.mdand tally the grade balance (supporting vs challenging, by grade). - Run the six-question bias audit before scoring. Write the answers down.
- Score the three exit questions, each with its best available evidence grade attached:
- Is the problem real and specific? — requires grade A
- Does the solution address the actual problem discovery revealed? — requires A or B
- Is there enough signal to justify building?
- Check the step-0 kill criteria. A criterion met outweighs a favorable-looking scorecard — that's what writing them in advance was for.
- Write the verdict to
DECISION.md, append toVENTURE.md's decision log, and state it to the founder plainly and unsoftened.
Verdicts: PROCEED · ITERATE · PIVOT · KILL · BLOCKED (no interviews yet — the only honest verdict when the ledger has no grade-A rows).
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.
- 6d ago First seen · 22 lines · 15 tokens per session scan A 40b35fa4b94e
idea-gate is a command published in the GitHub repository heyparsadev/claude-idea-validator (1 stars, last pushed 25d ago), licensed MIT. It adds 15 tokens to every session and 301 once invoked, about $0.0001 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
check-dev
Type-check a Z specification with fuzz.