Agent Authentication
ruvnet/ruflo
Agent skill for authentication - invoke with $agent-authentication
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…
Apache-2.0Auto-check passed
Install Decision API
$ npx skills add OpenAgentsInc/openagents --skill decision-api -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OpenAgentsInc/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/.agents/skills/decision-api .claude/skills/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 "decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/.agents/skills/decision-api into .claude/skills/decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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/.agents/skills/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 decision-api -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OpenAgentsInc/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/.agents/skills/decision-api .agents/skills/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 "decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/.agents/skills/decision-api into .agents/skills/decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 decision-api -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OpenAgentsInc/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/.agents/skills/decision-api .cursor/skills/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 "decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/.agents/skills/decision-api into .cursor/skills/decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 .agents/skills/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 decision-api -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OpenAgentsInc/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/.agents/skills/decision-api .gemini/skills/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 "decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/.agents/skills/decision-api into .gemini/skills/decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 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 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/.agents/skills/decision-api .github/skills/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 "decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/.agents/skills/decision-api into .github/skills/decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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 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 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/.agents/skills/decision-api .opencode/skills/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 "decision-api" agent skill from https://github.com/OpenAgentsInc/openagents/tree/main/.agents/skills/decision-api into .opencode/skills/decision-api/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "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
decision-api- GitHub stars
- 455
- Token cost
- ~1k tokens
- SKILL.md length
- 420 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
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…
- Caller needs a programmatic decision — routing
- SKILL.md covers The contract, Refusals, retries, and identity, The CLI and the SDK and What an answer does not mean, plus 1 more section
- Calls cargo; needs OPENAGENTS_API_KEY
- Verification — from a deployed door
What it does
Decision API is an agent skill from 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 typed refusals, Retry-After, and idempotent retries. Use it when an agent or caller needs a programmatic decision — routing, tagging, ranking, verification — from a deployed door, or when writing client code against crates/jev or the oak CLI.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The licence is Apache-2.0.
When your agent uses it
- Caller needs a programmatic decision — routing
- Verification — from a deployed door
- Writing client code against crates/jev
Example prompts
- “/decision-api”
Requirements
- A credential in OPENAGENTS_API_KEY
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
Shell commands in SKILL.md call:
cargo
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
Decision API loads about 1k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 420 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). 420 words, ~1,047 tokens.
Download SKILL.mdSave it as
.claude/skills/decision-api/SKILL.md (or your agent's skills folder).- name
- decision-api
- description
- 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 typed refusals, `Retry-After`, and idempotent retries. Use it when an agent or caller needs a programmatic decision — routing, tagging, ranking, verification — from a deployed door, or when writing client code against `crates/jev` or the `oak` CLI.
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 (noulfield, 0–1).choice— pick one ofcriteria's named options (choice,confidence,probabilities).score— probability-weighted position on 2–10 orderedcriterialevels (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.
Show full SKILL.md (193 more words)Show less
The CLI and the SDK
oak (cargo run -p oak) is the reference caller: oak ask --questions FILE [STATE] for one call, --input lines|ndjson for bounded batches,
--request-id for idempotent work, --select/--uncertain-below to shape
output, and stable exit codes (0 answered, 1 failure, 2 usage, 3 refused,
4 unavailable, 5 mixed). Credentials come from OPENAGENTS_API_KEY or a
0600 config file — never a flag. In Rust, crates/jev is the SDK the
CLI is built on.
What an answer does not mean
Probabilities are model judgments, not permission or proof of correctness.
Calibration must be measured on the target workload; the wire contract does
not establish it. A Noul of 0.5 expresses equal model probability for yes and no,
not an independently established frequency.
confidence describes how concentrated a distribution is. Acting on an
answer — a threshold, a routing rule, an escalation — belongs to the
caller's policy and should be measured on the caller's labelled data.
Where to read more
docs/decision-models/guides/caller.md— the caller's guide end to end.docs/decision-models/service/gateway.md— the service's admission, bounds, and refusal codes.docs/decision-models/api/openapi.yaml— the machine-readable contract.docs/decision-models/examples/— runnable curl andoakexamples.docs/gym/measured-records.md— how suites, runs, and report commitments measure a door.
© 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 .agents/skills/decision-api of OpenAgentsInc/openagents.
Open the folder on GitHubat commit ad9f02f
Compare with similar skills
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 |
|---|---|---|---|---|---|---|
| Decision API this skillOpenAgentsInc/openagents | 455 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Agent Authenticationruvnet/ruflo | 74k | 3 repos | ~711 | Automated safety check: Pass | MIT | |
| Accessible Authentication Reviewthedaviddias/Front-End-Checklist | 74k | — | ~579 | Automated safety check: Pass | MIT | |
| Authenticationlatitude-dev/latitude-llm | 4.7k | — | ~303 | Automated safety check: Pass | MIT | |
| Detecting Anomalous Authentication Patternsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~7.5k | Automated safety check: Pass | Apache-2.0 | |
| Implementing Zero Knowledge Proof For Authenticationmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~858 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Accessible Authentication Review
thedaviddias/Front-End-Checklist
Reviews sign-in, MFA, CAPTCHA and recovery flows for accessibility barriers such as blocked paste, memorized codes and transcription, and suggests fixes.
Authentication
latitude-dev/latitude-llm
Sessions, sign-in/sign-up flows, OAuth, magic links, or organization context on the session.
Detecting Anomalous Authentication Patterns
mukul975/Anthropic-Cybersecurity-Skills
Detects anomalous authentication patterns using UEBA analytics, statistical baselines, and machine learning models to identify impossible travel, credential stuffing, brute force, password spraying…
Implementing Zero Knowledge Proof For Authentication
mukul975/Anthropic-Cybersecurity-Skills
Implements the Schnorr identification protocol and a simplified Zero-Knowledge Password Proof (ZKPP) over the discrete logarithm problem, letting a prover authenticate by demonstrating knowledge of…
OmniRoute Authentication
diegosouzapw/OmniRoute
Documents how OmniRoute authenticates requests: Bearer credentials for the API, management-password login with session cookies, CSRF tokens and optional OIDC for the dashboard.
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.
Google Developer Style
OpenAgentsInc/openagents
Apply the Google Developer Documentation Style Guide to user-facing docs, READMEs, AGENTS.md, and commit messages.
Openagents Decision API
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.
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…
Questions about Decision API
What does Decision API do?
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…. Decision API is an agent skill from 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 typed refusals, Retry-After, and idempotent retries.
When should I use Decision API?
Decision API fits situations like: caller needs a programmatic decision — routing; verification — from a deployed door; writing client code against crates/jev.
How do I install Decision API in Claude Code?
Run `npx skills add OpenAgentsInc/openagents --skill decision-api -a claude-code`. Or copy the skill folder (.agents/skills/decision-api in OpenAgentsInc/openagents) into .claude/skills/decision-api in your project. Claude Code loads it when a task matches its description.
How do I install Decision API in Codex?
Run `npx skills add OpenAgentsInc/openagents --skill decision-api -a codex`. Or copy the skill folder (.agents/skills/decision-api in OpenAgentsInc/openagents) into .agents/skills/decision-api in your project. Codex loads it when a task matches its description.
Can I use 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 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/decision-api, .gemini/skills/decision-api, .github/skills/decision-api and .opencode/skills/decision-api in your project.
What does Decision API need to run?
Going by SKILL.md and its folder, Decision API needs the command-line tools its instructions call (cargo) and credentials named OPENAGENTS_API_KEY. Our summary lists: A credential in OPENAGENTS_API_KEY.
Does 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 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 Decision API use?
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 Decision API use?
About 1k tokens (SKILL.md is roughly 4.2k 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 Decision API?
Skills that share tags, products or a category with Decision API: Agent Authentication (ruvnet/ruflo, 74k stars), Accessible Authentication Review (thedaviddias/Front-End-Checklist, 74k stars), Authentication (latitude-dev/latitude-llm, 4.7k stars) and Detecting Anomalous Authentication Patterns (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains 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.