MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Authenticate to and call the OpenAgents decision API — typed decisions, batch classification, durable jobs, and the bundled documentation — through the oak CLI, the oak-mcp server, or raw HTTP.
Install Openagents Decision API
$ npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OpenAgentsInc/openagents openagents-decision-api --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/skills/openagents-decision-api .claude/skills/openagents-decision-api && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "openagents-decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-api into .claude/skills/openagents-decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openagents-decision-api", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-apiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OpenAgentsInc/openagents openagents-decision-api --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/skills/openagents-decision-api .agents/skills/openagents-decision-api && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "openagents-decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-api into .agents/skills/openagents-decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openagents-decision-api", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OpenAgentsInc/openagents openagents-decision-api --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/skills/openagents-decision-api .cursor/skills/openagents-decision-api && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "openagents-decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-api into .cursor/skills/openagents-decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openagents-decision-api", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OpenAgentsInc/openagents.git --path plugins/skills/openagents-decision-api--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OpenAgentsInc/openagents openagents-decision-api --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/skills/openagents-decision-api .gemini/skills/openagents-decision-api && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "openagents-decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-api into .gemini/skills/openagents-decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openagents-decision-api", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OpenAgentsInc/openagents openagents-decision-apiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/skills/openagents-decision-api .github/skills/openagents-decision-api && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "openagents-decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-api into .github/skills/openagents-decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openagents-decision-api", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OpenAgentsInc/openagents openagents-decision-api --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenAgentsInc/openagents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/skills/openagents-decision-api .opencode/skills/openagents-decision-api && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "openagents-decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/plugins/skills/openagents-decision-api into .opencode/skills/openagents-decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openagents-decision-api", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
openagents-decision-api- GitHub stars
- 455
- Token cost
- ~680 tokens
- SKILL.md length
- 309 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Authenticate to and call the OpenAgents decision API — typed decisions, batch classification, durable jobs, and the bundled documentation — through the oak CLI, the oak-mcp server, or raw HTTP.
- Works in 3 steps: A base URL from the operator — there is… → An oak_. bearer key issued by the… → A door name — GET /v1/models with your…
- A task needs a programmatic judgment
- SKILL.md covers What you need first, Ways to call, Reading answers and Limits
- Needs OPENAGENTS_API_KEY
What it does
Openagents Decision API is an agent skill from OpenAgentsInc/openagents. Authenticate to and call the OpenAgents decision API — typed decisions, batch classification, durable jobs, and the bundled documentation — through the oak CLI, the oak-mcp server, or raw HTTP. Use when a task needs a programmatic judgment, ranking, label, or verification from a deployed door.
Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. It works with Model Context Protocol. The licence is Apache-2.0.
When your agent uses it
- A task needs a programmatic judgment
- Verification from a deployed door
Example prompts
- “/openagents-decision-api”
Requirements
- A credential in OPENAGENTS_API_KEY
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- A base URL from the operator — there is no hosted public endpoint
- An oak_. bearer key issued by the operator. Put it in
- A door name — GET /v1/models with your key lists the doors you may
What it can do on your machine
Read from SKILL.md and the folder at commit ad9f02f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENAGENTS_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Openagents Decision API loads about 680 tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 309 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from OpenAgentsInc/openagents at commit ad9f02f, republished under its Apache-2.0 licence (© OpenAgentsInc). 309 words, ~680 tokens.
Download SKILL.mdSave it as
.claude/skills/openagents-decision-api/SKILL.md (or your agent's skills folder).- name
- openagents-decision-api
- description
- Authenticate to and call the OpenAgents decision API — typed decisions, batch classification, durable jobs, and the bundled documentation — through the oak CLI, the oak-mcp server, or raw HTTP. Use when a task needs a programmatic judgment, ranking, label, or verification from a deployed door.
OpenAgents decision API
A keyed HTTP service. A caller posts a state plus a map of typed
questions — noul (yes/no), choice, and score — and gets one typed
answer per question with probabilities. Batch classification runs
openagents.classify.v1 envelopes; durable jobs persist batches.
What you need first
- A base URL from the operator — there is no hosted public endpoint and no signup flow.
- An
oak_<id>.<secret>bearer key issued by the operator. Put it inOPENAGENTS_API_KEYor theapi_keyfield of~/.config/openagents/oak.json(mode0600). Never pass it in a URL, a flag, or a tool argument. - A door name —
GET /v1/modelswith your key lists the doors you may name asmodel.
Ways to call
- oak CLI —
oak ask --state state.json --questions questions.jsonfor one call;oak ask --input lines|ndjsonfor a bounded ordered batch;oak modelsto list doors;oak classifyfor the classification facade. - oak-mcp / oak-mcp-http — MCP over stdio or Streamable HTTP:
classify_texts,classify_dimensions,classify_multi_label,count_labels,review_uncertain,decide,list_models, and the credential-free documentation tools. The HTTP transport takes the caller bearer per request atPOST /mcp. - Raw HTTP —
POST /v1/systemone,POST /v1/classify,POST /v1/jobs,GET /v1/models,GET /v1/docs. See the origin'sopenapi.yamlandapi-catalog.json.
Reading answers
- Answered questions carry
answerfields per type; probabilities are part of the answer, not a side channel. - Refusals are typed JSON — a stable
codenaming why, never an HTML error.429and temporary-capacity codes are retryable; keep theIdempotency-Keyand bumpx-attempton retry. GET /v1/docs,/v1/docs/{id},/v1/docs/search, and/v1/docs/examplesread the bundled documentation without a credential.
Limits
- Discovery documents (
/agents.md,/auth.md,/api-catalog.json,/.well-known/agent-card.json) describe implemented behavior only; the catalog'sunimplementedlist names what does not exist — no OAuth, no streaming, no image input, no self-serve signup. - Inference consumes quota and can cost money even when nothing on the
network changes;
GET /v1/balanceexists only where the operator enabled monetary admission.
© OpenAgentsInc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/skills/openagents-decision-api of OpenAgentsInc/openagents.
Open the folder on GitHubat commit ad9f02f
Compare with similar skills
Openagents Decision API next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Openagents Decision API this skillOpenAgentsInc/openagents | 455 | — | ~680 | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 37k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | 1 repos | ~823 | Automated safety check: Pass | Apache-2.0 | |
| MemPalace Memory SearchMemPalace/mempalace | 59k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
MemPalace Memory Search
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
More from OpenAgentsInc/openagents
Typesafe AI
OpenAgentsInc/openagents
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.
Decision API
OpenAgentsInc/openagents
Call the OpenAgents decision API: authenticate with an oak bearer key, post state + typed questions to POST /v1/systemone, read Noul, Choice, and Score answers with their probabilities, and handle…
Google Developer Style
OpenAgentsInc/openagents
Apply the Google Developer Documentation Style Guide to user-facing docs, READMEs, AGENTS.md, and commit messages.
Nostr
OpenAgentsInc/openagents
How Nostr works in this repository: the three NIP lanes under nips/, the wire protocol (NIP-01), relay authentication (NIP-42), payload encryption (NIP-44), the Block agent NIPs the relay serves…
Related
Works with
Categories
Questions about Openagents Decision API
What does Openagents Decision API do?
Authenticate to and call the OpenAgents decision API — typed decisions, batch classification, durable jobs, and the bundled documentation — through the oak CLI, the oak-mcp server, or raw HTTP. Openagents Decision API is an agent skill from OpenAgentsInc/openagents. Authenticate to and call the OpenAgents decision API — typed decisions, batch classification, durable jobs, and the bundled documentation — through the oak CLI, the oak-mcp server, or raw HTTP.
When should I use Openagents Decision API?
Openagents Decision API fits situations like: A task needs a programmatic judgment; verification from a deployed door.
How do I install Openagents Decision API in Claude Code?
Run `npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a claude-code`. Or copy the skill folder (plugins/skills/openagents-decision-api in OpenAgentsInc/openagents) into .claude/skills/openagents-decision-api in your project. Claude Code loads it when a task matches its description.
How do I install Openagents Decision API in Codex?
Run `npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a codex`. Or copy the skill folder (plugins/skills/openagents-decision-api in OpenAgentsInc/openagents) into .agents/skills/openagents-decision-api in your project. Codex loads it when a task matches its description.
Can I use Openagents Decision API in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenAgentsInc/openagents --skill openagents-decision-api -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openagents-decision-api, .gemini/skills/openagents-decision-api, .github/skills/openagents-decision-api and .opencode/skills/openagents-decision-api in your project.
What does Openagents Decision API need to run?
Going by SKILL.md and its folder, Openagents Decision API needs credentials named OPENAGENTS_API_KEY. Our summary lists: A credential in OPENAGENTS_API_KEY.
Does Openagents Decision API access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Openagents Decision API safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Openagents Decision API use?
Openagents Decision API is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Openagents Decision API use?
About 680 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Openagents Decision API?
Skills that share tags, products or a category with Openagents Decision API: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Openagents Decision API?
OpenAgentsInc (a GitHub organization) maintains it in OpenAgentsInc/openagents, which has 455 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.
Source: OpenAgentsInc/openagents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.