rome: Skill for Claude Code

.claude/skills/validate-oauth-integration/SKILL.md

validate-oauth-integration is a skill for Claude Code from rome-os/rome. It costs 138 tokens per session (1,956 once invoked), scanned B, original, MIT.

A procedure for testing an OAuth connection, where a user grants an application permission to call another service on their behalf.

In plain words
What is it for?
Checking OAuth adapters locally, testing the real consent flow when credentials are available, and confirming that Rome can use the delegated token.
Why use it?
It verifies the complete path from clicking Connect through consent, token storage, and a real provider API call instead of relying only on code checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is rome-os/rome's own configuration. It tells Claude Code how to work on rome 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 rome configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rome-os/rome. 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/rome-os/rome/main/.claude/skills/validate-oauth-integration/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rome-os/rome

Made for: Claude Code.

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 validate-oauth-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/rome-os/rome/validate-oauth-integration.svg)](https://agentmods.dev/skills/rome-os/rome/validate-oauth-integration)
Your own site
<a href="https://agentmods.dev/skills/rome-os/rome/validate-oauth-integration"><img src="https://agentmods.dev/badge/skills/rome-os/rome/validate-oauth-integration.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,956 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 80
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Privilege Escalation · line 80
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Tool Misuse · line 80
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
How audits are shown
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 $0.00138 $0.01956
Opus 5 $0.00069 $0.00978
Sonnet 5 $0.00028 $0.00391
Haiku 4.5 $0.00014 $0.00196

Measured 8d ago against content hash 5ef8d5074094, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

validate-oauth-integration scanned grade B 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 8d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **The token write fails *after* the email gate passes if `/run/rome` is read-only.** The daemon runs uid 501; the `/run/rome` tmpfs must be world-writable (`mode=1777` in `compose.dev.yml`) or redeem throws `EACCES` on
.claude/skills/validate-oauth-integration/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate an OAuth integration

Goal end-state proven: a user opens Settings → Connections, clicks Connect , approves on the provider's consent screen, and Rome holds a delegated token it can call the provider's API with. The recipe is provider-agnostic — only the creds and the registered redirect URL change per provider. Slack (PR #1225) is the worked example throughout.

Validate in three escalating layers. Run them in order; each is cheaper to debug than the next. Report honestly which layers actually ran — Layer 2 needs a registered app, creds, and a human at the consent screen, so it is often where the human takes over.

The cross-service round-trip Layer 2 exercises:

dashboard ──▶ core /api/oauth/<provider>/start ──▶ Pantheon /start
  ──▶ provider authorize (real consent) ──▶ Pantheon /oauth/<provider>/callback
  ──▶ exchangeCode + fetchProfile (verified-email gate) ──▶ broker handoff
  ──▶ dashboard /callback ──▶ core /oauth/redeem ──▶ token persisted + token file

Layer 0 — Static + unit (host, fast)

  • pnpm typecheck (all workspaces).
  • Touched suites: the Pantheon adapter (pnpm --filter rome-pantheon exec vitest run src/lib/oauth), the core provider lists (pnpm --filter @rome/core exec vitest run src/lib/oauth-providers.test.ts), and the connector (pnpm --filter @rome/app-connector exec vitest run) if the token-consumer half exists.
  • Update the drift guards the new provider trips: the enabled-provider lists in packages/core/src/lib/oauth-providers.test.ts and the Rome-managed lists in rome_apps/connector/src/web/lib/connections.test.ts. Any test that used the service as a stand-in Composio toolkit must switch to a still-Composio one (e.g. notion).

Layer 1 — Token usage, no OAuth dance (fast confidence in the consumer code)

Mint a token out-of-band and prove Rome can use it, decoupled from the consent flow:

  • In the provider's developer console, "Install to Workspace" (or equivalent) to mint a token without the redirect flow.
  • Write it into the rome container by hand at /run/rome/<provider>-oauth-token (single string, or JSON for multi-token services like Slack's {botToken,userToken,teamId}).
  • Ask the agent to run connector_proxy against a read endpoint (an auth.test-equivalent) and a write endpoint.

Read the full file on GitHub · 98 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. 8d ago First seen · 98 lines · 138 tokens per session scan B 5ef8d5074094

Subscribe to this mod's changes

validate-oauth-integration is a skill published in the GitHub repository rome-os/rome (482 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 1,956 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

langbot-eba-adapter-dev

Build, refactor, and test LangBot platform adapters for the Event-Based Agents architecture. Use when adding or migrating Telegram, Discord, or other messaging platform adapters to the EBA adapter layout, validating unified event/message conversion, writing live adapter probes, or using standalone plugin runtime plus…

langbot-app/LangBot · 73 tokens

langbot-dev

Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…

langbot-app/LangBot · 136 tokens

browserwing-executor

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

MemTensor/MemOS · 42 tokens

data-leakage-detection

Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.

Tencent/AI-Infra-Guard · 34 tokens

groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

synthetic-sciences/openscience · 77 tokens

agentfield

Design and ship a multi-agent system on AgentField. Use when the user asks to build, scaffold, design, or run an agent, reasoner network, multi-agent backend, or 'an agent that does X' — whenever the work would otherwise be a single LLM call or a flat LangChain/CrewAI/AutoGen chain. The skill produces composite…

Agent-Field/agentfield · 127 tokens