Borrowing it
Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. 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/noizu-labs-ml/NoizuPromptLingo/main/.claude/commands/init-project-fast.mdgit clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingoWrote 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/noizu-labs-ml/noizupromptlingo/init-project-fast)<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/init-project-fast"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/init-project-fast/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/commands/noizu-labs-ml/noizupromptlingo/init-project-fast"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/init-project-fast.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 | $0.00062 | $0.03570 |
| Opus 5 | $0.00031 | $0.01785 |
| Sonnet 5 | $0.00012 | $0.00714 |
| Haiku 4.5 | $0.00006 | $0.00357 |
Grade C, and why
init-project-fast scanned grade C with 1 finding 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 7d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .npl/project-init/ How it starts
The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Project (Fast)
Bootstrap project documentation with progressive artifact generation and interstitial working files.
Outputs: CLAUDE.md, docs/PROJECT-ARCH.md, docs/PROJECT-LAYOUT.md
Design Philosophy
no-coordinator : Launch scouts directly — no pre-scan, no orchestration overhead
progressive : Generate drafts as scouts report, refine incrementally
interstitial
: Working files in .npl/project-init/ visible during execution, cleaned up at end
minimal-viable
: Skeleton docs that can be expanded via /update-arch and /update-layout
Phase 1: Initialize Environment
Initialize CLAUDE.md and prepare interstitial workspace:
- Use the
NPLLoadMCP tool to load minimal NPL dependencies:NPLLoad(expression="syntax fences directives") - Use directory exploration tools (Glob, Bash
tree) for directory structure exploration
Create interstitial workspace: mkdir -p .npl/project-init/synthesis
Version Handling
The init-claude command uses versioned prompt sections with npl-instructions: YAML headers. Behavior depends on existing CLAUDE.md state:
First-time initialization (no versioned sections):
- Appends all default prompts automatically
- Exit code 1 (changes made)
Existing versioned sections:
- Prints version comparison table (source vs installed)
- Exits without modifying (exit code 2 if updates available, 0 if current)
- User must explicitly choose to update
Write coordination state:
// .npl/project-init/meta.json
{
"session_start": "<timestamp>",
"scouts_launched": [],
"scouts_complete": [],
"stack_detected": null,
"synthesis_started": false
}
CLAUDE.md receives:
- NPL Conventions (visualization preferences, tools)
- NPL Load Directive
- NPL Scripts reference
- SQLite Quick Guide
Phase 2: Direct Scout Deployment
🎯 Launch all 4 scouts in a single parallel batch. No coordinator, no pre-scan.
Scout Consolidation
| Scout | Merged From | Domain | Key Targets |
|---|---|---|---|
| Scout-Foundation | Structure + Layers | Project skeleton, tech stack, layer boundaries | tree, manifests, entry points, config |
| Scout-Core | Domain + Patterns | Business logic, code patterns, testing | src/, lib/, domain code, tests |
| Scout-Infra | Services + DevOps | Infrastructure, deployment, external services | docker, k8s, ci/cd, database |
| Scout-Surface | API | Public interfaces, contracts, documentation | routes, openapi, README |
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.
- 7d ago First seen · 562 lines · 62 tokens per session scan C c1b16c835240
init-project-fast is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 3,570 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.