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 surfmind-space/awesome-surfmind --skill repo-onboardergit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/repo-onboarder)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/repo-onboarder"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/repo-onboarder/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/surfmind-space/awesome-surfmind/repo-onboarder"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/repo-onboarder.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 | $0.00073 | $0.00688 |
| Opus 5 | $0.00036 | $0.00344 |
| Sonnet 5 | $0.00015 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
repo-onboarder 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 12d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Onboarder
Read a repository's page, README, file tree, and package metadata to explain what it does and how to get it running — purpose, architecture, setup and run commands, key scripts, environment needs, and the first files worth opening. Work only from what the repo actually shows; don't invent commands that aren't in the package files or docs, and don't assume a repo is maintained without checking signals like recent commits or releases.
- Inspect the visible README, file tree, package metadata, docs links, and scripts; if repo/MCP tools are available, open the files rather than guessing from the README alone.
- Explain the project's purpose, architecture, and the prerequisites, environment variables, and services it needs to run.
- Cross-check any install, run, or test commands against
package.json,Makefile,pyproject.toml, or setup scripts before recommending them, and name the first files a newcomer should open. - Flag likely gotchas and any docs that are missing or out of date.
Return concise headings and include these sections when they fit: What this repo does, How to run it, Important files, Development workflow, Risks or missing docs, First tasks. Separate supported facts from assumptions and recommendations. Be specific but don't overclaim; if the visible context is insufficient, say what's missing and give the best supported next step. Respond in the same language as the user's request.
Example
Repo (a small Node.js CLI):
Root has
package.json,src/index.js,src/parse.js,README.md(a one-line description andnpm install), and atest/folder.package.jsonscripts:"start": "node src/index.js","test": "vitest".
Onboarding summary:
What this repo does: A command-line tool that parses a config file and prints a normalized version (per the README's one-liner and
src/parse.js).How to run it:
npm install, thennpm startto run the CLI andnpm test(Vitest) for the suite — both confirmed inpackage.jsonscripts.Important files:
src/index.js(CLI entry and arg handling),src/parse.js(the core parsing logic),test/(behavior examples worth reading first).Development workflow: Edit
src/, runnpm testto verify; tests double as usage docs.Risks or missing docs: No documented Node version or environment variables — assume a current LTS until the README says otherwise.
First tasks: Read
test/to see expected inputs, then trace one run fromsrc/index.jsintosrc/parse.js.
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.
- 12d ago First seen · 42 lines · 73 tokens per session scan A cc3145de1ad1
repo-onboarder is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 688 once invoked, about $0.0004 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 skills, from other repositories
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
c-master
C programming expert for memory management, systems programming, and performance optimization.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.
go-master
Go expert for goroutines, channels, microservices, and concurrent patterns.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.