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 skills add aneja5/forge-skills --skill idea-grillergit clone --depth 1 https://github.com/aneja5/forge-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/aneja5/forge-skills/idea-griller)<a href="https://agentmods.dev/skills/aneja5/forge-skills/idea-griller"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/idea-griller/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/skills/aneja5/forge-skills/idea-griller"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/idea-griller.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 | $0.00065 | $0.01343 |
| Opus 5 | $0.00032 | $0.00672 |
| Sonnet 5 | $0.00013 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
idea-griller 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Griller
Overview
Pressure-test a raw idea through Socratic questioning. One question per turn, each built from the user's last answer. Output is .forge/idea-brief.md — a structured brief that lets spec-driven-development skip discovery and go straight to requirements.
When to Use
- User describes a new idea, project, or feature they haven't fully thought through
- User wants to stress-test assumptions before writing a spec
- Idea is vague, contradictory, or needs a sharper scope
When NOT to Use
.forge/prd.mdalready exists — the idea is past this stage- User is reporting a bug — use
debugging-and-recovery - Idea is already well-specified with named users, clear scope, and a distribution plan
Common Rationalizations
| Thought | Reality |
|---|---|
| "The idea is obvious, let's skip to the spec" | Obvious ideas carry the most unchecked assumptions |
| "The user knows what they want" | They know symptoms — root cause is often different |
| "One more question is too many" | Vague answers compound — drill until specific |
| "I can infer the business model" | Never infer. Ask. You will be wrong. |
| "The MVP is clear" | MVPs defined without drilling risks are over-scoped |
| "We can resolve distribution later" | If you can't name channel + motion now, the idea isn't ready |
| "We covered the important branches" | Important by whose criteria? Distribution and Risks are the most-skipped and the most-costly to miss. |
Red Flags
- User says "everyone" or "all users" — no segment identified
- Answer to distribution is "word of mouth" or "social media" — not a plan
- MVP scope grows across turns — riskiest assumption not isolated
- User can't name a single person who has this problem today
- Business model is "we'll figure it out later"
- Founder fit answer is "I'm passionate about this space"
- Interview stopped before all 7 branches because "the idea is clear enough" or "we ran out of time"
Behavior Rules
- One question per turn. Always.
- Generate each question from the user's last answer — never from a fixed script
- If vague or contradictory: drill deeper on the same branch
- If clear and specific: acknowledge briefly (one line), advance to next branch
- Max 3 questions per branch — don't loop forever
- Push back on weak answers. "People want this" requires evidence.
- Note unresolved items as open assumptions in the brief
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.
- 6d ago First seen · 126 lines · 65 tokens per session scan A d035bad3c809
idea-griller is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 1,343 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.