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 sitegit 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/site)<a href="https://agentmods.dev/skills/arcblock/agent-skills/site"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/site/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/arcblock/agent-skills/site"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/site.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 | $0.00069 | $0.01668 |
| Opus 5.5 | $0.00028 | $0.00667 |
| Sonnet 5.5 | $0.00014 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
site 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 1mo 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.
ARC skill: site
Cold-read agents often miss the full-site path (theme + multi-page via
create-site), mix up disk build output with what HTTP is serving, and
mix up daemon :4900 with the Web Device site host port. This booklet
is the L0 map. Prefer live arc afs explain /web after a daemon is up
(arc skill show daemon).
Prefer
arc skill list→ this booklet for create-site / whole site / serve vs build / URLs- Live:
arc afs explain /webthenarc afs explain /web/.actions/create-site - After a site exists:
arc afs exec /web/sites/<name>/.actions/doctor(site doctor — not top-levelarc doctor) - No dangling links:
arc afs exec /web/sites/<name>/.actions/check-links - Persist durable content:
arc skill show space· search:arc skill show index
Critical path facts (do not invent)
| Wrong (404 / missing) | Correct on a typical daemon |
|---|---|
list /.library/themes |
list /web/.library/themes |
explain /.library/themes/{name} |
explain /web/.library/themes/{name} |
storage: "/storage" on a new instance |
storage: "/work" (writable host work root) |
/storage is not a default system mount. Theme library is under the /web
mount. Writable storage on a fresh instance is /work.
Serve vs build
build writes static HTML to .web/.build on disk. declare starts an HTTP
host with its own lifecycle (in-memory SiteServer). A successful build does
not reload HTTP. If disk .web/.build is a new revision but
http://<site>.localhost:<web-port>/en/ still shows the old page, the host is
stale.
arc afs exec /web/sites/<name>/.actions/doctor --instance <name>
# FAIL + remediation → reload the host:
arc afs exec /web/.actions/undeclare --instance <name> --args '{"name":"<site>"}'
arc afs exec /web/.actions/declare --instance <name> --args '{"name":"<site>","source":"/work/<site>"}'
Accept-path: healthy site (HTTP matches disk) passes. Stale-serve fails with undeclare+declare — never a silent success.
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.
- 1mo ago First seen · 156 lines · 69 tokens per session scan A b32f9d78815b
site is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 69 tokens to every session and 1,668 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.