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.
git clone --depth 1 https://github.com/indranildchandra/claude-local-starterWrote 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/indranildchandra/claude-local-starter/init-repo)<a href="https://agentmods.dev/commands/indranildchandra/claude-local-starter/init-repo"><img src="https://agentmods.dev/badge/commands/indranildchandra/claude-local-starter/init-repo/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/indranildchandra/claude-local-starter/init-repo"><img src="https://agentmods.dev/badge/commands/indranildchandra/claude-local-starter/init-repo.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 | $0.00047 | $0.01221 |
| Opus 5 | $0.00023 | $0.00611 |
| Sonnet 5 | $0.00009 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
init-repo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are bootstrapping Claude Code for this project. Follow all steps in order.
Step 1 — Understand the project (3 parallel subagents)
Spawn these simultaneously and wait for all three to complete before proceeding.
Subagent A — Structure
- Run
npx gitnexus analyzeto build the initial code knowledge graph - List all top-level directories and identify sub-module boundaries
- Read any existing README.md, CLAUDE.md, or docs/ at root
- Report: tech stack, architecture pattern, key entry points
Subagent B — Dependencies
- Read package.json / requirements.txt / go.mod / Cargo.toml / pom.xml (whichever exist)
- Identify all external third-party integrations (APIs, SDKs, cloud services, auth providers)
- Note internal microservices separately
- Report: external integrations that will need live Context7 doc fetches before working on them
Subagent C — Conventions
- Read any .eslintrc, .prettierrc, pyproject.toml, Makefile, CI config files
- Check git log (last 20 commits) for coding patterns and commit message conventions
- Identify test framework, test directory structure, and how to run tests
- Report: conventions, patterns, what to preserve
Step 2 — Create project root CLAUDE.md
Using findings from Step 1, create a CLAUDE.md tailored to this project.
Do not copy a generic template — every section must reflect what was actually found.
Required sections:
- Project Overview — what the system does, who uses it, scale/criticality
- Architecture — key services, boundaries, data flow; reference gitnexus graph
- Tech Stack — languages, frameworks, databases, infra; specific versions where relevant
- External Integrations — each external system, what it does, which service owns it; note that live Context7 docs must be fetched before working on any of these
- Internal Services — internal sub-modules and their responsibilities
- Sub-module CLAUDE.md Index — list created below; update as new ones are added
- Conventions — coding standards, naming, preferred patterns
- Test Strategy — framework, how to run tests (single test and full suite), coverage expectations
- Key Commands — build, test, lint, deploy commands specific to this project
- Known Constraints — performance, security, regulatory constraints, tech debt to avoid
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 First seen · 121 lines · 47 tokens per session scan A a9b90ea34c2f
init-repo is a command published in the GitHub repository indranildchandra/claude-local-starter (13 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,221 once invoked, about $0.0002 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 2026-08-30.
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.