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 ArcBlock/agent-skills --skill repo-setupgit clone --depth 1 https://github.com/ArcBlock/agent-skillsWrote 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/arcblock/agent-skills/repo-setup)<a href="https://agentmods.dev/skills/arcblock/agent-skills/repo-setup"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/repo-setup.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.01586 |
| Opus 5 | $0.00034 | $0.00793 |
| Sonnet 5 | $0.00013 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
repo-setup scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
*this* platform (macOS → `brew`, Debian/Ubuntu → `apt install -y`, `bun` → its curl installer), How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Setup — adopt the agentloop plugin in a repo
Run once per repo to go from "plugin installed" to "loop skills can actually run here".
The supporting environment the sweep/review skills assume (a repo-profile, the coordination
labels, a verify gate, a working toolchain + gh auth) is otherwise implicit — this makes it
explicit and reproducible. All scripts live in <plugin_root>/bootstrap/ and are idempotent
(the directory keeps its name: there it means "the scripts that bootstrap a repo", which is
unambiguous — the skill was renamed because /agentloop:bootstrap alone did not say what
it bootstrapped, and now pairs with /agentloop:fleet-setup).
This is hybrid by design. The split, and why it matters:
- Deterministic scripts lay down structure and auto-detect what can be mechanically probed (repo_slug, plugin_root, default_branch, package_manager, the fixed label set, the env assertions). They never guess values they can't ground in a file, and never mutate your system.
- You, the agent, do what needs judgement or side-effects: install missing tools, fill the profile fields that require reading the repo, write the real verification checks. Scripts hand you a stable skeleton; you supply the parts a script can't reliably infer.
This is adoption, not scheduling. How you run the skills on an interval (cron / CI / a cloud routine system) is your repo's own infra — see
docs/scheduling-recipe.md. Repo-setup deliberately does not touch that.
The flow (run from the consuming repo root, in order)
PR=<plugin_root> # from .claude/repo-profile.md, or wherever the plugin is checked out
Step 0 — preflight · script diagnoses, you repair
bash "$PR/bootstrap/check-env.sh"
check-env is a read-only probe: it reports what's missing and exits non-zero, but it never
installs anything. If it reports a missing tool, that's your cue to fix it — install it for
this platform (macOS → brew, Debian/Ubuntu → apt install -y, bun → its curl installer),
then re-run until green. The script even prints a suggested command per tool; you judge
platform / permissions / fallback and actually run it. (This mirrors CLAUDE.md's "install missing
CLI deps, don't give up" discipline — repairing the env is an agent action, not a script's.)
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.
- 6d ago First seen · 113 lines · 67 tokens per session scan A b209e2d5158d
repo-setup is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 1,586 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…