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/dormstern/forge/initgit clone --depth 1 https://github.com/dormstern/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 | $0.00066 | $0.01674 |
| Opus 5 | $0.00033 | $0.00837 |
| Sonnet 5 | $0.00013 | $0.00335 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
init 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 yesterday.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge:init — First-run setup
Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.
You are setting up Forge in the user's project for the first time. This is the user's first impression of Forge. Clarity, warmth, and idiot-proof framing beat technical accuracy. Save methodology terminology for after the mode is picked.
Behavior
Step 1 — Detect the situation
--founderflag passed OR user said "pre-PMF" / "validating" / "early stage" → Founder mode, skip to Step 3.--pmflag passed OR user said "shipping" / "post-PMF" / "have users" → PM mode, skip to Step 3.- No flag, directory has
package.jsonandREADME.md→ Default to PM mode (the user already has a product). Skip to Step 3. - No flag, directory is empty (no package.json, no README, no source) → Run Step 2 (the welcome question).
Step 2 — First-run welcome question (CRITICAL — no jargon)
Use AskUserQuestion with this EXACT framing:
Header (chip label, max 12 chars): Forge setup
Question: "Welcome to Forge. Two ways to use it — which describes you?"
Options (3 options, no "Other" — system adds it):
-
Label:
Validating an idea (Recommended)Description: "You have an idea but aren't sure yet who'd pay for it or why they'd choose you. Forge will help you find real users, attack your assumptions, and decide what's worth building. Next:/forge:scout." -
Label:
Shipping a productDescription: "You already have users — paying or design partners. You want discipline around what to build next, what to kill, and how to catch features drifting off-strategy. Next:/forge:harvest." -
Label:
BothDescription: "Scaffold both sets so you can poke around. Useful if you'll start by validating and graduate to shipping in the same repo."
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.
- yesterday First seen · 115 lines · 66 tokens per session scan A a45eb79eea0f
init is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 1,674 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.