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/collaborategit 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 | $0.00018 | $0.01531 |
| Opus 5 | $0.00009 | $0.00766 |
| Sonnet 5 | $0.00004 | $0.00306 |
| Haiku 4.5 | $0.00002 | $0.00153 |
Grade A, and why
collaborate 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Collaborate
Activates hackathon-native multiplayer mode: N users on different machines brain-dump ideas, AI consolidates into categorized tasks, tasks dispatch across machines via a distributed claim queue, each agent squash-merges its own completed task. Forward-motion during execute: AI picks + flags decisions, humans override async.
Prerequisites
Two transport modes are supported. Pick one BEFORE running /forge:collaborate start:
- Realtime (Ably) — sub-second cross-machine latency via WebSockets. Requires:
- The
ablynpm package installed:npm install ablyin your project (or globally). It's declared an OPTIONAL peerDependency in the plugin'spackage.json, so/forge:collaborate starthard-fails with "forge:collab realtime mode requires theablypeer dependency" until you install it. - An Ably API key in your environment:
export ABLY_KEY="<your-key>". Free tier at https://ably.com/sign-up covers typical hackathon teams (6M messages/month, 200 peak connections).
- The
- Polling (zero-setup) — coordination via a dedicated
forge/collab-stategit branch, ~2.5s latency. No extra dependencies, no API keys. Pass--pollingto/forge:collaborate startto opt into this path even whenABLY_KEYis in env.
If neither is configured and --polling is not passed, start prints a setup guide and exits.
Subcommands
| Command | What it does |
|---|---|
/forge:collaborate start |
Initialize collab state, print session code derived from repo's origin URL |
/forge:collaborate join |
Sync with existing session in this repo (git pull + subscribe) |
/forge:collaborate brainstorm |
Enter chat-mode brain-dump; agent iterates with you and writes .forge/collab/brainstorm/inputs-<handle>.md on accept |
/forge:collaborate status |
Show participants online, active claims, open flags |
/forge:collaborate claim <taskId> |
Explicitly reserve a specific task |
/forge:collaborate flags |
List all forward-motion flags with status |
/forge:collaborate override <flagId> <new-decision> |
Override an AI decision, mark flag overridden |
/forge:collaborate leave |
Release claims and disconnect |
/forge:collaborate recover |
Diagnose and repair a stale collab session (crash between start/leave steps) |
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 · 111 lines · 18 tokens per session scan A e169f1f1844e
collaborate is a command published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,531 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.