openagents: Skill for Claude Code

.agents/skills/decision-api/SKILL.md

decision-api is a skill for Claude Code, Codex from OpenAgentsInc/openagents. It costs 113 tokens per session (1,088 once invoked), scanned A, original, Apache-2.0.

A client for a decision service that answers typed questions about supplied data instead of generating a conversation. It sends a state and questions to an API and reads condition probabilities, choices, or scores.

In plain words
What is it for?
It helps agents or applications ask independent questions about text or JSON, authenticate with a bearer key, inspect available models, and process typed answers with probabilities.
Why use it?
It provides a defined request and response format for programmatic decisions, including authentication, refusals, retry timing, and safe repeat requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is OpenAgentsInc/openagents's own configuration. It tells Claude Code and Codex how to work on openagents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openagents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to OpenAgentsInc/openagents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OpenAgentsInc/openagents/main/.agents/skills/decision-api/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/OpenAgentsInc/openagents

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for decision-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/openagentsinc/openagents/decision-api/github.svg)](https://agentmods.dev/skills/openagentsinc/openagents/decision-api)
Your own site
<a href="https://agentmods.dev/skills/openagentsinc/openagents/decision-api"><img src="https://agentmods.dev/badge/skills/openagentsinc/openagents/decision-api/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for decision-api

Your own site · 80×15
<a href="https://agentmods.dev/skills/openagentsinc/openagents/decision-api"><img src="https://agentmods.dev/badge/skills/openagentsinc/openagents/decision-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.01088
Opus 5.5 $0.00045 $0.00435
Sonnet 5.5 $0.00023 $0.00218
Haiku 4.5 $0.00011 $0.00109

Measured 27d ago against content hash 3555f9489469, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

decision-api scanned grade A with 1 finding 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 27d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `docs/decision-models/examples/` — runnable curl and `oak` examples.
.agents/skills/decision-api/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The decision API for callers

The service answers questions instead of generating text. One request carries one state (the JSON or text under judgment) and a map of typed questions; the response carries one typed answer per question with probabilities. There is no streaming prose and no chat history — each call is complete and independent.

The contract

POST /v1/systemone
Authorization: Bearer oak_<id>.<secret>
Content-Type: application/json

{
  "model": "shared-kev",
  "state": "I was charged twice on the March invoice.",
  "questions": {
    "refund": {"type": "noul", "instructions": "Does the customer ask for money back?"}
  }
}
{"model": "shared-kev", "answers": {"refund": {"type": "noul", "noul": 0.91}},
 "usage": {"input_tokens": 412, "output_tokens": 2}}

GET /v1/models lists the doors the credential may name in model. Three question types:

  • noul — probability a condition holds (noul field, 0–1).
  • choice — pick one of criteria's named options (choice, confidence, probabilities).
  • score — probability-weighted position on 2–10 ordered criteria levels (score, confidence, probabilities, legend).

Question ids are caller-side only — the model sees instructions and criteria, never the id. Include a no-match option in a choice when nothing may fit.

Refusals, retries, and identity

Errors are typed: {"error": {"code", "message"}}. Gateway-owned codes are stable (unauthenticated, door_not_bound, invalid_request, too_many_questions, too_many_options, idempotency_conflict, rate_limited, busy, overloaded, quota_exhausted, door_unavailable, identity_mismatch, unavailable); a backend may add its own refusal codes. Treat rate_limited/busy/overloaded and 5xx as retryable — honor Retry-After — and quota_exhausted as a daily budget that retrying cannot fix.

Send Idempotency-Key on work you may retry and increment X-Attempt per attempt: the service settles quota by (request, attempt), a retried request shares one reservation, and a settled pair reused against changed content answers 409. The x-request-id response header is the identity to quote when reporting a call.

Read the full file on GitHub · 101 lines

Changes

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.

  1. 27d ago Changed · +2 lines 3555f9489469
  2. 1mo ago First seen · 99 lines · 113 tokens per session scan A f2e478f0eb58

Subscribe to this mod's changes

decision-api is a skill published in the GitHub repository OpenAgentsInc/openagents (458 stars, last pushed today), licensed Apache-2.0. It adds 113 tokens to every session and 1,088 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

dev-runtime

How the Node side of a dev stack runs without haven, and the backend host: pnpm dev (UI built once, backend reloading), pnpm dev:hmr (adds the Vite ui lane), tools/dev-runtime (api + worker in one Node process), backend reload on a file change, the debounce (quiet window + max wait), ports derived from PORT. Use when…

langwatch/langwatch · 172 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens