connect-apps

A one-time connection process for linking an administrator-approved online service to a user's account through OAuth, a sign-in method that lets the service grant access without sharing a password.

In plain words
What is it for?
Connecting an available SaaS app so its tools can be used in one-to-one conversations.
Why use it?
It lets the user authorize an app without giving the agent their password. The user approves the connection in a browser.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yc-software/qm/connect-apps
Any agent
npx skills add yc-software/qm --skill connect-apps
Clone the repo
git clone --depth 1 https://github.com/yc-software/qm

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 318 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00022 $0.00318
Opus 5 $0.00011 $0.00159
Sonnet 5 $0.00004 $0.00064
Haiku 4.5 $0.00002 $0.00032

Measured 3d ago against content hash db8dc8118970, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connect-apps 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 3d 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.

curl -sS -X POST "$AGENT_API_URL/v1/connectors/oauth/consent/mint" \
skills-seed/connect-apps/SKILL.md · 23 lines

What it actually says

Connecting SaaS apps

When $AGENT_OAUTH_CONSENT_TOKEN is set you can help the user connect a SaaS app via a browser consent link they tap — you never see or enter their password. The live Connected apps block is the source of truth: offer only providers configured by the admin, and offer none when that list is empty. Mint a single-use link for the selected provider, then give the user the full URL to open: curl -sS -X POST "$AGENT_API_URL/v1/connectors/oauth/consent/mint"
-H "X-Agent-Capability: $AGENT_OAUTH_CONSENT_TOKEN" -H 'content-type: application/json'
-d '{"provider":""}'

  • The response has connectUrl — give the user THAT exact URL (it is the full public tap-through link). Do NOT build it yourself or prepend $AGENT_API_URL — that private base isn't reachable from a browser.
  • If mint returns oauth_not_configured, the admin has not enabled that app. Do not suggest it, retry it, or re-send old links.
  • You cannot open the link yourself; relay the URL, tell them to tap Allow, then return. After they connect, the app's tools/skills work in your 1:1s with them.
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. 3d ago First seen · 23 lines · 22 tokens per session scan A db8dc8118970

Subscribe to this mod's changes

connect-apps is a skill published in the GitHub repository yc-software/qm (14,428 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 318 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

address-feedback

Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.

pydantic/pydantic-ai · 29 tokens

agent-initialization

Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.

Prism-Shadow/penguin-harness · 30 tokens

agent-mode

Unified tool for managing agent LLM modes (add, remove, update, list, switch).

PhyAgentOS/PhyAgentOS-core · 22 tokens