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/ankushdixit/claude-plugins/initgit clone --depth 1 https://github.com/ankushdixit/claude-pluginsWhat 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 | $0.00012 | $0.01147 |
| Opus 5 | $0.00006 | $0.00574 |
| Sonnet 5 | $0.00002 | $0.00229 |
| Haiku 4.5 | $0.00001 | $0.00115 |
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template-Based Project Initialization
Initialize a new Solokit project with guided template selection for production-ready setup.
Interactive Template Selection (4 Questions)
Use the AskUserQuestion tool to collect all configuration:
Question 1: Project Category
Question: "What type of project are you building?" Header: "Category" Multi-Select: false
Options:
-
Label: "SaaS Application" Description: "T3 stack with Next.js, Prisma, tRPC - Full-featured web apps with auth, payments, multi-tenancy"
-
Label: "ML/AI Tooling" Description: "FastAPI with Python ML libraries - Machine learning APIs, data pipelines, model serving"
-
Label: "Internal Dashboard" Description: "Refine with React admin framework - Admin panels, analytics dashboards, internal tools"
-
Label: "Full-Stack Product" Description: "Next.js with full-stack capabilities - General purpose web applications"
Question 2: Quality Gates Tier
Question: "What level of quality gates do you want?" Header: "Quality Tier" Multi-Select: false
Options:
-
Label: "Essential" Description: "Linting, formatting, type-check, basic tests (fastest setup)"
-
Label: "Standard" Description: "+ Git hooks (Husky), security scanning (recommended for most projects)"
-
Label: "Comprehensive" Description: "+ Coverage reports, integration tests, mutation testing (production-ready)"
-
Label: "Production-Ready" Description: "+ Performance monitoring, error tracking, deployment safety (enterprise-grade)"
Question 3: Testing Coverage Target
Question: "What testing coverage level do you want to enforce?" Header: "Coverage" Multi-Select: false
Options:
-
Label: "Basic (60%)" Description: "Minimal coverage for prototypes and MVPs"
-
Label: "Standard (80%)" Description: "Industry standard for production code (recommended)"
-
Label: "Strict (90%)" Description: "High-reliability applications and mission-critical systems"
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 · 167 lines · 12 tokens per session scan A 69b50a1c2e67
init is a command published in the GitHub repository ankushdixit/claude-plugins (3 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,147 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 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.