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 agentmods add skills/cloudflare/agents/workspace-digestnpx skills add cloudflare/agents --skill workspace-digestgit clone --depth 1 https://github.com/cloudflare/agentsWhat 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 | $0.00040 | $0.00242 |
| Opus 5 | $0.00020 | $0.00121 |
| Sonnet 5 | $0.00008 | $0.00048 |
| Haiku 4.5 | $0.00004 | $0.00024 |
Grade A, and why
workspace-digest 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 3d 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.
What it actually says
Workspace Digest
Produce a concise inventory of the files saved in this assistant's shared workspace (the same workspace every chat under this user shares).
Process
- Run
scripts/digest.tsto scan the workspace and build a file inventory. Pass{ "dir": "/some/path" }to scope the scan to a subdirectory. - Summarize the result for the user: how many files, the notable ones, and the total size.
- Offer to open or read any specific file the user is interested in.
The TypeScript script is function-style (export default run(input, ctx)). It
reads the workspace through ctx.workspace (read-only) and a formatting hint
bundled alongside the skill via ctx.files.
Output format
Keep the digest short - a markdown list of files with sizes, plus a one-line summary. Only print the full listing if the user asks for it.
What ships with it
2 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.
- 3d ago First seen · 27 lines · 40 tokens per session scan A cabb88258971
workspace-digest is a skill published in the GitHub repository cloudflare/agents (5,503 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 242 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
one
Use the One CLI (one) to interact with 3rd-party platforms — Gmail, Slack, Stripe, Notion, etc. through their APIs. One handles auth, request building, and execution. TRIGGER when: Interact with ANY 3rd-party platform or external service (e.g., "send an email", "create a Shopify order", "find a HubSpot contact", "post…
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
mochi-slack
Slack awareness — unread mentions, channel digests, topic radar, thread summaries. Load when user asks about Slack.
meetings
Context for working with the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks, and calendar cache live, what the lifecycle states mean, and how the app's agents are driven. Load when the user asks about a meeting's notes or action items, or when writing/reading files under the meetings…