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 ForgeyClap/claude-forge --skill forge-brainstormgit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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/forgeyclap/claude-forge/forge-brainstorm)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-brainstorm"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-brainstorm/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/forgeyclap/claude-forge/forge-brainstorm"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-brainstorm.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 | $0.00039 | $0.00734 |
| Opus 5.5 | $0.00016 | $0.00294 |
| Sonnet 5.5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
forge-brainstorm 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 20d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Structured ideation (brainstorm before build)
Do not duplicate ECC skills — defer to: brainstorming (the deep design-dialogue methodology; it ships with Forge as a pinned vendored skill). This
file is the Forge-specific orchestration wrapper: a compact diverge → converge loop sized for a /forge
work package rather than a full standalone design doc.
Hard rules
- No implementation before a written pick + rationale. Even a "simple" task benefits from naming the 2-3 real alternatives and why one was chosen — unexamined assumptions on "simple" work cause the most rework.
- If the request is genuinely ambiguous in a way that changes the answer, ask the ONE most
decision-changing question before diverging (superseded 2026-09: the owner's
intakeconfig default issilent, capping the whole build at at most one owner question total — this skill does not get its own separate question budget); otherwise pick the sensible default, state it, and proceed — never silently guess on something consequential. - Constraints are gathered from real project evidence (existing architecture, stack,
CLAUDE.md,FORGE_PROJECT_PROFILE.md) — not invented defaults that ignore the actual codebase. - Do not over-invest: this is a short loop, not a multi-day design-doc process. Match the depth to the
task's real complexity/risk (see the fan-out table in
CLAUDE.md).
The loop (diverge → constraints → converge → smallest viable first)
- Diverge. List 2-4 genuinely different approaches (not trivial variations of the same one). For each: name and what it is · why it could work here · real cost (time/complexity/risk) · one risk it does not address — side by side, so hidden assumptions show.
- Constraints. Apply what actually limits the choice here: existing architecture/conventions, stack, team size/skills available, time/complexity budget (fan-out level), security/compliance posture, anything the owner already ruled out.
- Converge. Pick one approach and give the rationale in 1-3 sentences — why this one beats the alternatives for this project, not in the abstract. Name what was explicitly rejected and why.
- Smallest viable first. Scope the smallest slice that proves the approach works end-to-end before building the full version — the first work package should be small enough to verify quickly, not the whole feature at once.
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.
- 20d ago Changed 7b71fd5740f4
- 25d ago Changed · +2 lines 0040c5342323
- 26d ago Changed dc9c5b534a72
- 1mo ago First seen · 45 lines · 39 tokens per session scan A 530f52343cbb
forge-brainstorm is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 21d ago), licensed MIT. It adds 39 tokens to every session and 734 once invoked, about $0.0002 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 skills, from other repositories
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
trailhead-view
Skill "trailhead-view" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, render the map: map [map], 🎯 destination and 🗒️ notes.
review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
implement-comment
Use when operating as the Fabrik Implement comment reviewer. This skill guides applying user-requested code changes during implementation, committing and pushing, and updating the task checklist — without signaling stage completion.
specify
Use when operating as the Fabrik Specify stage agent. This skill guides the specification and clarification of a feature request, turning a rough backlog issue into a clear, unambiguous spec before technical research begins.