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 skills/luiseiman/dotforge/init-projectnpx skills add luiseiman/dotforge --skill init-projectgit clone --depth 1 https://github.com/luiseiman/dotforgeWhat 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 | $0.00028 | $0.02224 |
| Opus 5 | $0.00014 | $0.01112 |
| Sonnet 5 | $0.00006 | $0.00445 |
| Haiku 4.5 | $0.00003 | $0.00222 |
Grade A, and why
init-project 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init Project
MANDATORY FLOW: detect stack → ask 4 questions → WAIT for answers → generate config.
You MUST ask the 4 questions in Step 4 and WAIT for the user to answer BEFORE generating any files. Do NOT skip the questions. Do NOT generate config before receiving answers.
Step 1: Check if already initialized
If .claude/settings.json exists:
Already initialized. Use /forge sync to update or /forge audit to check score.
Exit without changes.
Step 2: Detect stacks
Scan project files silently using $DOTFORGE_DIR/stacks/detect.md as reference:
python-fastapi: pyproject.toml, requirements.txt with fastapi
react-vite-ts: package.json with react + vite
swift-swiftui: Package.swift, *.xcodeproj
node-express: package.json with express/fastify (no react)
go-api: go.mod
java-spring: pom.xml or build.gradle with spring
supabase: supabase/ dir or supabase in deps
docker-deploy: Dockerfile or docker-compose*
gcp-cloud-run: app.yaml or cloudbuild.yaml
aws-deploy: cdk.json or template.yaml
redis: redis in deps
data-analysis: *.ipynb prominent
devcontainer: .devcontainer/
Also scan existing files for additional context:
- README.md → project description
- existing test files → testing patterns
- CI config (.github/workflows, Makefile) → build/test commands
Step 3: Detect user language and ask 4 questions
Detect language: check previous messages → global CLAUDE.md → system locale → default English.
OVERRIDE RULE: For /forge init, ALWAYS present questions in the detected language, even if global CLAUDE.md says "communicate in Spanish/English/etc." The questions are part of the tool's UI, not a conversation.
Present all 4 questions together in one message. Then STOP and WAIT for the user's response. Do NOT proceed to Step 5 until the user answers.
English version:
═══ FORGE INIT ═══
Stack detected: {stacks or "none — generic config"}
4 quick questions to generate a complete config:
1. What does it do and what does it NOT do?
→ One sentence: the problem it solves, and explicit limits of v0.1.
Example: "REST API for real-time quotes. No auth, no frontend, no historical data yet."
2. Built with what?
→ Stack, language, DB, external services, where it runs.
Example: "Python 3.12, FastAPI, Supabase, deployed on GCP Cloud Run."
3. How do you work?
→ Solo or team, spec-first or prototype-first, testing level from day one.
Example: "Solo, prototype-first, tests only for critical paths."
4. What domain and role?
→ What expertise does Claude need? What business concepts are critical?
Example: "Expert in Jira API v3, agile metrics, dashboard generation.
Key concepts: velocity, cycle time, sprint burndown, JQL."
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 · 231 lines · 28 tokens per session scan A 6ac8c9ab7c35
init-project is a skill published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 2,224 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 2026-08-31.
Other skills, from other repositories
scaffold
Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
find-opps
Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…