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 web-workspace-onboardinggit 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/web-workspace-onboarding)<a href="https://agentmods.dev/skills/arcblock/agent-skills/web-workspace-onboarding"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/web-workspace-onboarding.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 | $0.00073 | $0.01422 |
| Opus 5 | $0.00036 | $0.00711 |
| Sonnet 5 | $0.00015 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
web-workspace-onboarding 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Workspace Onboarding
This is an entry and routing skill. Let the target workspace own its product facts, writing standards, storage layout, review process, and validation commands. Do not duplicate or override those project-native rules here.
Read the workspace contract before creating a durable project profile or preparing a handoff. Use the bundled profile template only after the user authorizes a project-local profile.
1. Establish the workspace boundary
- Identify the access source: local checkout, supplied directory, MCP resource, AFS mount, or a repository that must first be checked out. Verify the source instead of assuming that a visible directory is the project root.
- Locate the narrowest owning workspace and inspect its top-level instructions before reading
unrelated files. Look for
AGENTS.md,CLAUDE.md, repository profiles, and scoped instruction files in the affected subtree. - Record existing working-tree changes before writing. Preserve them unless the user explicitly asks to change or discard them.
- Use the project-provided access method. Do not require a clone when a readable MCP or AFS source already exposes the authoritative files.
Classify the result:
- Declared: a project profile or explicit instructions identify the content/workflow contract.
- Discoverable: instructions and project layout reveal enough contract to route the current task safely.
- Partial: the workspace can be read but lacks enough authority, storage, or validation detail.
- Unavailable: the source cannot be read or its boundary is ambiguous.
For Partial or Unavailable workspaces, explain the missing contract and ask the smallest necessary question before making a project change. Do not guess a publishing path or a canonical fact source.
2. Build a workspace map
Read only the files needed to build this compact map:
| Map field | Establish from evidence |
|---|---|
| Workspace and scope | Project root, task subtree, access source, dirty-state boundary |
| Instruction hierarchy | Root and scoped instructions, including which rule wins on conflict |
| Fact authority | Current author statements, canonical product/profile sources, implementation, historical references |
| Task routes | Local skills for writing, translation, review, code, media, and release work |
| Delivery contract | Content roots, schema/frontmatter, tags, locales, output paths, validation commands |
| Approval boundary | What may be drafted, written, committed, or externally published |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 131 lines · 73 tokens per session scan A e2eaa39670a0
web-workspace-onboarding is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 1,422 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
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…