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/anythink-cloud/anythink-cli/anythinknpx skills add anythink-cloud/anythink-cli --skill anythinkgit clone --depth 1 https://github.com/anythink-cloud/anythink-cliWhat 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 | $0.00199 | $0.01804 |
| Opus 5 | $0.00100 | $0.00902 |
| Sonnet 5 | $0.00040 | $0.00361 |
| Haiku 4.5 | $0.00020 | $0.00180 |
Grade A, and why
anythink 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anythink
Anythink is a deep, all-in-one backend platform. A single project gives you:
typed data modelling (22+ field types, relationships, polymorphic refs),
row- and field-level security, full-text + semantic + geo search,
RBAC (roles, permissions, API keys), a workflow/automation engine,
third-party integrations (Claude, OpenAI, Slack, Google, GitHub…), file
storage, and payments. Your job is to drive that platform competently —
and the way you do almost everything is the MCP's cli tool.
The cli tool is the whole platform
The MCP exposes a few dedicated tools for auth and context — login /
logout, config_show/use/remove, accounts_*, projects_*. Everything
else is done through the generic cli tool, which runs any anythink
command and returns its output: entities, fields, data, search, workflows,
roles, users, api-keys, files, integrations, pay, oauth, menus, secrets,
migrate, api, docs.
- Pass the command exactly as you'd type it after
anythink— e.g. theclitool withentities list, ordata create posts --data '{"title":"Hi"}'. - Don't include
anythinkitself or--profile(the active profile is injected for you). - The CLI can do everything the Anythink API can do, so the
clitool can too. If you're reaching for some other mechanism to talk to Anythink, you're almost certainly meant to usecliinstead.
(On the CLI directly, these are the same commands without the tool wrapper:
anythink entities list, etc. See references/setup.md.)
Discover the live surface — don't guess
The platform is broad and evolves, and it documents itself. Before composing non-trivial commands, read the live reference instead of guessing flags:
cli→docs --json— the full, authoritative command + capability reference, built for AI tooling. (docsfor markdown.)cli→<group> --help— exact flags for a command, e.g.entities --help,fields add --help,search query --help.cli→api --json— every REST endpoint.
What ships with it
4 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.
- 2d ago First seen · 155 lines · 199 tokens per session scan A ecd9becbda17
anythink is a skill published in the GitHub repository anythink-cloud/anythink-cli (6 stars, last pushed 5d ago), licensed MIT. It adds 199 tokens to every session and 1,804 once invoked, about $0.0010 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…