Borrowing it
Nothing to install: this file belongs to Aptica-Solutions/a-mcp-runmeter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Aptica-Solutions/a-mcp-runmeter/main/.claude/commands/project-init.mdgit clone --depth 1 https://github.com/Aptica-Solutions/a-mcp-runmeterWrote 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/commands/aptica-solutions/a-mcp-runmeter/project-init)<a href="https://agentmods.dev/commands/aptica-solutions/a-mcp-runmeter/project-init"><img src="https://agentmods.dev/badge/commands/aptica-solutions/a-mcp-runmeter/project-init.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01022 |
| Opus 5 | $0.00000 | $0.00511 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
project-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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow these steps in order. Do not skip ahead or begin coding. This is an initialization and discovery flow.
Step 1 — Load Context
Read these files before doing anything else:
CLAUDE.md(project root)_engineer/ENGINEER-README.md_engineer/ENGINEER-FLOW.md_engineer/ONBOARDING.template.md_engineer/REQUIREMENTS.template.md
Step 2 — Prove Understanding
After reading, output a brief confirmation (8–12 bullet points) covering:
- The non-negotiable guardrails: secrets, PHI, destructive commands
- The "no code before approved survey" rule — state it explicitly
- The engineer flow sequence (ONBOARDING → REQUIREMENTS → Plan → Code → Tests)
- The task tracking convention: file, status symbols, PBI markers
- The commit convention (PBI boundary, format, co-author line)
- The session checkpoint signal and when to use it
- The ADO sync trigger and command
- Any files that are missing or unreadable (flag now, before proceeding)
Then ask the user: "Do you confirm I have correctly understood the project rules? (yes / correct me)"
Wait for the user's response. If they correct you, update your understanding and re-confirm before continuing.
Step 3 — Interactive Survey
Ask each section of the survey one at a time. Do not present all questions at once.
Walk through these sections in order, waiting for the user's answer before moving to the next:
- Project Identity (name, entity)
- AI Tooling (which AI assistants will be used)
- Project Type (backend, frontend, full stack, infra, etc.)
- Tech Stack (backend language/framework, frontend, database, cloud)
- Compliance Requirements (HIPAA, SOC 2, PCI DSS, None)
- Log Destination (Application Insights, Log Analytics, file, other)
- Auth Requirements (none, Entra/OAuth, API key, other)
- Integration Points (external systems this project will connect to)
- Special Concerns (constraints, risks, non-standard requirements)
After all sections are answered:
- Present the complete filled-in survey for the user to review
- Ask: "Is this survey accurate? (yes to confirm / tell me what to change)"
- Apply any corrections
- Write the completed survey to
ONBOARDING.mdin the project root - Record sign-off by creating the marker
_engineer/.onboarding-complete. This retires the onboarding gate for the repo — the survey-gate hook stops running once the marker exists. Commit the marker so the whole team skips the gate, or add it to.gitignoreto keep sign-off per-developer. - Confirm: "ONBOARDING.md written and onboarding signed off."
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.
- 5d ago First seen · 114 lines · 0 tokens per session scan A f97dd0a6e018
project-init is a command published in the GitHub repository Aptica-Solutions/a-mcp-runmeter (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,022 tokens. 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 2026-09-01.
Other commands, from other repositories
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
design-ship
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…
compact-prep
Ask the agent to prepare for conversation compaction by updating any relevant state and providing guidance for the compaction agent and to kick off the session there after.
code-review
Code review a pull request.
extract-qa
Extract all Q&A pairs (AskUserQuestion interactions) from the current session.