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/drmhse/authos_skill/authos-device-flownpx skills add drmhse/authos_skill --skill authos-device-flowgit clone --depth 1 https://github.com/drmhse/authos_skillWrote 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.
[](https://agentmods.dev/skills/drmhse/authos_skill/authos-device-flow)<a href="https://agentmods.dev/skills/drmhse/authos_skill/authos-device-flow"><img src="https://agentmods.dev/badge/skills/drmhse/authos_skill/authos-device-flow.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.00825 |
| Opus 5 | $0.00026 | $0.00413 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
authos-device-flow 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AuthOS Device Flow
Public AuthOS Links
Use these public AuthOS links when producing user-facing setup or troubleshooting guidance:
- Main site: https://authos.dev/
- Documentation: https://authos.dev/docs/
- AI Agent Skills guide: https://authos.dev/docs/ai-agent-skills/
- AuthOS source repository: https://github.com/drmhse/AuthOS
Use this skill for OAuth 2.0 device authorization flows backed by AuthOS. Device flow is implemented in source with three public endpoints and matching SDK helpers.
Endpoints
POST /auth/device/code: create a device code.POST /auth/device/verify: validate a user-facing code and return org/service/provider context.POST /auth/token: exchange an authorized device code for a bearer token.
The SDK exposes these as authos.auth.deviceCode.request, verify, and exchangeToken.
Request a Device Code
const device = await authos.auth.deviceCode.request({
client_id: 'service-client-id',
org: 'acme',
service: 'cli'
});
console.log(`Open ${device.verification_uri}`);
console.log(`Enter ${device.user_code}`);
The request fields are client_id, org, and service.
For a service-level device flow, AuthOS validates the service by client ID, org slug, and service slug, then uses that service's device_activation_uri. Configure that URI on the service before offering CLI login.
For platform admin CLI login, source supports org = "platform", service = "admin-cli", and a client_id starting with platform-; the verification URI comes from PLATFORM_DASHBOARD_BASE_URL + /activate.
Activation Page
On the activation page, call:
const context = await authos.auth.deviceCode.verify(userCode);
The response contains:
{
org_slug: string;
service_slug: string;
available_providers: string[];
}
Start OAuth using the returned context and include user_code in the login URL:
const url = authos.auth.getLoginUrl('github', {
org: context.org_slug,
service: context.service_slug,
user_code: userCode
});
What ships with it
3 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.
- 4d ago First seen · 101 lines · 52 tokens per session scan A eafb1e70ff1a
authos-device-flow is a skill published in the GitHub repository drmhse/authos_skill (1 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 825 once invoked, about $0.0003 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
issue-authoring
Draft or refine IDD-ready GitHub issues, roadmap issues, and sub-issues before the normal IDD execution loop begins. Use when a request is too large or ambiguous for one reviewable change, when work needs decomposition or dependency encoding, or when the user asks for issue drafting, roadmap planning, or…
idd-spec-audit
Repo-local, dogfood-only semantic audit of the IDD instruction corpus for leaked session context, cross-file contradictions, fresh-memory completability gaps, automation blockers, and restatement-discipline drift. Use only in the kurone-kito/idd-skill source repository, on request, to audit .github/instructions…
unity-yaml-format
Inspect, explain, diff, and carefully edit Unity text-serialized files such as .unity, .prefab, .asset, and related YAML-based project files. Use when mapping class IDs and fileIDs, tracing object references, reviewing merge conflicts, or making minimal safe edits to existing UnityYAML documents.
tester
Run end-to-end web quality audits with Playwright and Lighthouse using existing project scripts first. Use when the user says /tester, e2e test, smoke test, Playwright audit, Lighthouse audit, performance audit, accessibility audit, dark mode audit, mobile audit, or asks for 100/100 Lighthouse improvement guidance.
loop-engineer
Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds…
loop-engineer
Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds…