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 skills add n24q02m/claude-plugins --skill onboard-repogit clone --depth 1 https://github.com/n24q02m/claude-pluginsWrote 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/skills/n24q02m/claude-plugins/onboard-repo)<a href="https://agentmods.dev/skills/n24q02m/claude-plugins/onboard-repo"><img src="https://agentmods.dev/badge/skills/n24q02m/claude-plugins/onboard-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/skills/n24q02m/claude-plugins/onboard-repo"><img src="https://agentmods.dev/badge/skills/n24q02m/claude-plugins/onboard-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 | $0.00038 | $0.01565 |
| Opus 5.5 | $0.00015 | $0.00626 |
| Sonnet 5.5 | $0.00008 | $0.00313 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
onboard-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 4d 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.
This is a copy
100% identical to onboard-repo — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard Repo
Take a codebase you have never seen and turn it into a queryable graph, then read the graph to produce an orientation map. Use this on first contact with a repository, before answering questions about it or changing anything in it.
Scope: this skill builds and reads a knowledge graph. It does not modify source files, CI configuration, or project conventions. The only files it creates are the graph database under .crg/ (already self-ignored) and, when you choose to add one, a .code-review-graphignore.
Command surface: run the local CLI through the coding harness shell. Examples
use the installed crg command; from a source checkout,
prefix it with uv run. No MCP mapping is required.
Steps
-
Check what already exists with
crg graph stats --repo-root "<path>". A non-empty graph can go directly to step 5; a missing-graph error means continue with a build. -
Decide the indexing scope before building:
- Single repository: pass only
--repo-root "<path>". - A repository that vendors or embeds others: add a
.code-review-graphignoreat the repo root (onefnmatchpattern per line,#for comments) so vendored trees, build output, and fixtures do not inflate the graph. Common additions:vendor/*,third_party/*,**/generated/*,**/*.min.js. - Several sibling repositories that call each other: federate them in one graph with
--rootsin step 3, then useimpact-auditfor cross-repo questions.
- Single repository: pass only
-
Build the graph with
crg graph build --full-rebuild --repo-root "<path>".- For a federated build:
crg graph build --full-rebuild --repo-root "<path-a>" --roots "<path-b>". Each root is registered in the repo registry and its files are tagged with arepo_id, which later lets you scope any query with--repo "<repo_id>". - Parsing is Tree-sitter based and needs no language servers, toolchains, or compilation -- an unbuildable checkout still indexes.
- For a federated build:
-
Enable semantic search with
crg graph embed --repo-root "<path>". Without embeddings, the CLI's search action falls back to name and keyword matching, which will miss "where is authentication handled" style questions.- The default backend is local and requires no credentials. The graph-stats result reports the resolved backend and embedding count.
- If a cloud embedding chain is expected but stats show local, inspect the local environment/configuration rather than assuming the model list is wrong.
- Optional:
crg graph summarize --repo-root "<path>"adds generated summaries for function nodes, but only when a summarizer model chain is configured. It is a no-op otherwise -- do not report it as a failure.
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.
- 4d ago Changed 66bed50c32e5
- 1mo ago Changed 52d279cc4167
- 2mo ago First seen · 103 lines · 38 tokens per session scan A 9c53ca394db2
onboard-repo is a skill published in the GitHub repository n24q02m/claude-plugins (4 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,565 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to onboard-repo, differing in 28 lines, and is treated as a copy.
onboard-repo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onboard-repon24q02m/claude-plugins | Skill | 4 | today | Apache-2.0 | A | 38 | Claude Code |
| projectmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 475 | Claude Code |
| doc-html-slidemodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 438 | Claude Code |
| cs-channel-messagemodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 465 | Claude Code |
| media-higgsfield-explainermodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 244 | Claude Code |
| media-gpt-image-promptmodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 334 | Claude Code |
| career-portfoliomodu-ai/moai-cowork | Skill | 315 | 29d ago | Apache-2.0 | A | 124 | Claude Code |