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/lucasduys/forge/brainstormgit clone --depth 1 https://github.com/LucasDuys/forgeWhat 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 | $0.00010 | $0.00733 |
| Opus 5 | $0.00005 | $0.00367 |
| Sonnet 5 | $0.00002 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
brainstorm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Brainstorm
First-Run Wizard (R004.AC3)
Before anything else, fire the one-shot token-reduction wizard. Idempotent — prints once on first install, then no-ops forever. Suppressed when /forge:watch is rendering its own banner (R004.AC6).
node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-wizard.cjs" --forge-dir .forge
Step 1: Initialize project state
If .forge/ does not exist, initialize it:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/setup.sh" .
Step 2: Discover capabilities
Scan the user's environment for MCP servers, skills, and plugins:
node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-tools.cjs" discover --forge-dir .forge
This writes .forge/capabilities.json with available tools that can enhance brainstorming and execution.
Step 2.5: Auto-Detect Project Context
Before starting the interactive Q&A, automatically detect available context:
Design system: Check if DESIGN.md, design.md, or docs/DESIGN.md exists. If found, pass its path to the brainstorming skill so it can reference existing design constraints in the spec. If not found, the brainstorming skill will ask whether the user wants one (for UI projects).
Knowledge graph: Check if graphify-out/graph.json exists. If found, load the god nodes and community structure to inform the brainstorming Q&A with architecture context. This helps propose approaches that align with existing codebase structure.
Neither requires any user action. Detection is automatic and silent.
Step 3: Start brainstorming
IMPORTANT: The brainstorm phase is mandatory before planning and execution. The spec files produced by this workflow are the ONLY way to get status: approved specs, which are required by /forge plan and /forge execute. Do NOT skip this step. Do NOT write spec files directly without going through the full interactive brainstorm flow.
Now invoke the forge:brainstorming skill with the user's arguments, plus any auto-detected context (design system path, graph summary).
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.
- 2d ago First seen · 65 lines · 10 tokens per session scan A 4698d2b6c6f7
brainstorm is a command published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 733 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 2026-08-30.
Other commands, from other repositories
audit-system
Run a comprehensive audit of an existing design system for consistency, completeness, and accessibility.
build-presentation
Build a design presentation end to end — audience framing, narrative structure, and supporting rationale.
discover
Run a full user research cycle — persona creation, empathy mapping, and journey mapping for a product or feature.
interview
Prepare an interview script or summarize an interview transcript into structured insights.
deploy
Deploy the application to production.
eg-new-feature
Build a new feature using the elephant/goldfish workflow — design doc, goldfish design check, implement, review, validate.