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/deepdotspace/deepspace-skill/deepspacenpx skills add deepdotspace/deepspace-skill --skill deepspacegit clone --depth 1 https://github.com/deepdotspace/deepspace-skillWhat 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 | $0.00116 | $0.03344 |
| Opus 5 | $0.00058 | $0.01672 |
| Sonnet 5 | $0.00023 | $0.00669 |
| Haiku 4.5 | $0.00012 | $0.00334 |
Grade A, and why
deepspace 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 2d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSpace
DeepSpace is one package for real-time collaborative apps on Cloudflare
Workers. It provides auth, RBAC, synchronized records, messaging, integrations,
payments, and deploys to <name>.app.space.
This skill is the bootstrap: how to start, how to operate, and how to consult the documentation. The documentation at https://docs.deep.space is the authority for everything else — it is written to be opinionated, so when it recommends an approach, take that as the default rather than one option among many.
One source authority
Every app has exactly one Git authority — DeepSpace source (packaged,
commit-first) or GitHub source (manual; deploys ship the local working tree,
dirty bytes included) — and as of v0.26.0 it is inferred from use, never
declared. A checkout with a GitHub remote deploys as GitHub, no claim step;
the first deepspace push (or an unclaimed app's deploy sync) claims
DeepSpace source once, permanently — using it is choosing it, so never
run deepspace push on a GitHub-centric app unless the user has chosen to
adopt DeepSpace source. deepspace app source is read-only (the old setter
refuses source_inferred); there are no transfers. Never maintain two
sources of truth, and read the source-control and workspaces docs before any
source, push, pull, or clone operation — the docs, not this skill, state
what each verb does under each authority.
Sharing and handing over an app
Collaborators and ownership transfer (deepspace app collaborators …,
deepspace app transfer …) change who can deploy, read secrets, and own the
app. Read the app-identity guide before either — it states exactly what each
grant confers and what a transfer takes away — and treat both as decisions to
surface to the user, not steps to run in passing.
How to read the documentation
Consult the docs BEFORE building in an area, not after something breaks. The reading procedure:
- Fetch the index once per task area: https://docs.deep.space/llms.txt — generated from the docs on every deploy, so it is never stale — lists every page with a one-line summary.
- Pick 1–2 pages from it and fetch each as Markdown by appending
.mdto the page URL (https://docs.deep.space/guides/authentication.md). If the page you picked lacks the answer, do not wander adjacent pages — go to step 3. - To prove whether a topic exists at all, fetch
https://docs.deep.space/llms-full.txt once (the whole corpus in one
file; each page ends with
Source: /route.md) and grep it. A confirmed absence means the docs lag the build — fall back to the installed.d.tsor the CLI's own--help. - For point lookups within known topics, prefer MCP:
https://docs.deep.space/mcpexposesdocumentation_searchanddocumentation_read. Register it when your harness supports MCP servers, e.g.claude mcp add --transport http deepspace-docs https://docs.deep.space/mcp. Search finds the exact section when the topic exists; it cannot tell you a topic is absent — that is what step 3 is for. - For exact type signatures, read the installed package —
ls node_modules/deepspace/dist/*.d.ts(in the SDK monorepo itself:packages/deepspace/dist/) — authoritative when any doc lags the installed version.
What ships with it
1 file 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.
- 2d ago First seen · 272 lines · 116 tokens per session scan A 9962355c93ba
deepspace is a skill published in the GitHub repository deepdotspace/deepspace-skill (5 stars, last pushed 4d ago), licensed MIT. It adds 116 tokens to every session and 3,344 once invoked, about $0.0006 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.