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 luiseiman/dotforge --skill init-projectgit clone --depth 1 https://github.com/luiseiman/dotforgeWrote 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/luiseiman/dotforge/init-project)<a href="https://agentmods.dev/skills/luiseiman/dotforge/init-project"><img src="https://agentmods.dev/badge/skills/luiseiman/dotforge/init-project/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/luiseiman/dotforge/init-project"><img src="https://agentmods.dev/badge/skills/luiseiman/dotforge/init-project.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 | $0.00028 | $0.02293 |
| Opus 5.5 | $0.00011 | $0.00917 |
| Sonnet 5.5 | $0.00006 | $0.00459 |
| Haiku 4.5 | $0.00003 | $0.00229 |
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 9d 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 — 233 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.
If AGENTS.md exists (with or without a CLAUDE.md), say so before the questions: bootstrap will keep it and generate CLAUDE.md with an @AGENTS.md import (or write to the symlink target) instead of hiding it — see /bootstrap-project Step 3.
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.
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.
- 9d ago Changed · +2 lines aaf9a3a8fc2e
- 1mo 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 10d ago), licensed MIT. It adds 28 tokens to every session and 2,293 once invoked, about $0.0001 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
zephermine
Creates a persisted, sectionized implementation artifact suite through research, stakeholder interviews, domain analysis, database and API design, and multi-LLM review. Use for feature or product plans consumed by downstream implementation and QA. Prefer lightweight native plan/interview workflows for small tasks; on…
clio
A final-review and document-production workflow. It checks whether a process is ready to proceed, extracts source-based diagrams, and creates documents such as product requirements, technical documentation, and manuals.
design-plan
A design-system planning and implementation guide for frontend projects. A design system is a shared set of visual rules, reusable components, and accessibility practices for building consistent user interfaces.
frontend-design
A frontend design and implementation guide for turning a visual design plan into a working web interface. It also provides fallback guidance when an official design plugin is unavailable.
agent-team
A guide for coordinating a team of coding agents working on one task. It covers when to split work into parallel assignments, how a lead agent coordinates them, and how to record shared knowledge.
argos
A software inspection skill that checks an implementation against design documents such as API specifications, quality-assurance scenarios, flow diagrams, and other project specifications.