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/basher83/lunar-claudeWrote 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/basher83/lunar-claude/repo-onboard)<a href="https://agentmods.dev/commands/basher83/lunar-claude/repo-onboard"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/repo-onboard/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/basher83/lunar-claude/repo-onboard"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/repo-onboard.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 | $0.00007 | $0.01697 |
| Opus 5 | $0.00003 | $0.00848 |
| Sonnet 5 | $0.00001 | $0.00339 |
| Haiku 4.5 | $0.00001 | $0.00170 |
Grade A, and why
repo-onboard 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 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.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Onboard
Detect project type, run the appropriate mise preset chain, and migrate from pre-commit to hk if applicable.
Current State
- Working directory: !
pwd - Git repo: !
test -d .git && echo "Yes" || echo "No" - Existing mise.toml: !
test -f mise.toml && echo "Yes" || echo "No" - Existing hk.pkl: !
test -f hk.pkl && echo "Yes" || echo "No" - Pre-commit config: !
test -f .pre-commit-config.yaml && echo "Yes (migration candidate)" || echo "No"
Phase 1: Detect Project Type
Scan for project type indicators using Glob:
pyproject.toml,setup.py,setup.cfg→ PythonCargo.toml→ Rustpackage.json,bun.lock,bun.lockb,tsconfig.json→ Bun/TypeScript*.tffiles in the current or immediate subdirectories → Terraformansible.cfg,playbooks/directory,roles/directory → Ansible
A project may match multiple types (e.g., Python + Terraform monorepo). Track all matches. If nothing matches, the project is "base only".
Phase 2: Confirm with User
Confirm the detected configuration.
Build the question dynamically based on what was detected:
If project type(s) detected, present them. If .pre-commit-config.yaml exists, include migration in the confirmation. If hk.pkl already exists, note it will be overwritten.
Question format:
- header: "Onboard"
- question: "Detected: [type(s)]. [Migration note if applicable]. This will run preset:base + preset:[type], creating mise.toml, hk.pkl, .editorconfig, cliff.toml, .gitignore, and renovate.json. Proceed?"
- options:
- Proceed (Run detected preset chain)
- Base only (Skip language preset, run preset:base only)
- Cancel (Abort onboarding)
If multiple types detected, use multiSelect: true to let user choose which language presets to apply.
Phase 3: Execute Presets
Based on user confirmation, run the appropriate preset via Bash.
Available presets and their commands:
- Python:
mise preset:uv(depends on preset:base, runs both) - Rust:
mise preset:rust(depends on preset:base, runs both) - Bun/TypeScript:
mise preset:bun(depends on preset:base, runs both) - Terraform:
mise preset:terraform(depends on preset:base, runs both) - Ansible:
mise preset:ansible(depends on preset:base, runs both) - Base only:
mise preset:base
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 · 156 lines · 7 tokens per session scan A 781109b92cd3
repo-onboard is a command published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 1,697 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
handoff
Export a Waybill Bundle by default, or import one when requested.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.