agentmods.dev

connector-auth

connector-auth is a skill for Claude Code from wecode-ai/Wegent. It costs 16 tokens per session (437 once invoked), scanned A, original, Apache-2.0.

A handler for plugin operations that need a missing or expired login. It identifies the exact plugin and connector involved and stops that plugin's work until authentication is restored.

In plain words
What is it for?
Use it when a plugin explicitly reports that authentication is required, so the host can present the correct login request and resume afterward.
Why use it?
It prevents unrelated errors, such as network failures or permission denials, from being misreported as a login problem. It also avoids guessing which account or connector to use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions .claude-plugin; mentions Codex.

Part of the wework-runtime plugin — 7 skills shipped together

not rated 886repo +4 today A scan 16 tokens original Apache-2.0

Good fit Use it when a plugin explicitly reports that authentication is required, so the host can present the correct login request and resume afterward.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wecode-ai/wegent/connector-auth
View source ↗ wecode-ai/Wegent wecode-ai.github.io
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.

Any agent
npx skills add wecode-ai/Wegent --skill connector-auth
Clone the repo
git clone --depth 1 https://github.com/wecode-ai/Wegent

Made for: Claude Code.

Or install wework-runtime, the plugin that ships this one along with the rest of its 7 skills.

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 connector-auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/wecode-ai/wegent/connector-auth/github.svg)](https://agentmods.dev/skills/wecode-ai/wegent/connector-auth)
Your own site
<a href="https://agentmods.dev/skills/wecode-ai/wegent/connector-auth"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/connector-auth/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 connector-auth

Your own site · 80×15
<a href="https://agentmods.dev/skills/wecode-ai/wegent/connector-auth"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/connector-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00016 $0.00437
Opus 5.5 $0.00006 $0.00175
Sonnet 5.5 $0.00003 $0.00087
Haiku 4.5 $0.00002 $0.00044

Measured 2d ago against content hash 14bc147cda0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

connector-auth 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 2d 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.

wework/resources/bundled-plugins/wework-personal/plugins/wework-runtime/skills/connector-auth/SKILL.md · 15 lines

What it actually says

Wework local plugin authorization:

  • A plugin mention does not require an authentication preflight. Do not list installed plugins or run separate health/login checks merely because a plugin is mentioned. Use its business tools when the task needs them.
  • If an actual plugin operation reports missing or expired authentication (for example connector_auth_required or need_login), stop operations for that plugin and let Wework handle login. Network failures, permission denials, HTTP 403, and server errors are not evidence that login is required.
  • Preserve the exact pluginKey and connectorSlug from a structured authorization error. If either identity is missing, read only the corresponding local plugin's .codex-plugin/plugin.json or .claude-plugin/plugin.json to resolve its declared identity and connectors[].slug; require a declared localAuth connector. Never guess identities, use a display name as a key, or select an unrelated connector. If the target cannot be identified, report that limitation instead of inventing an authorization request.
  • For an identified local connector that needs login, end the turn with connector_auth_required, pluginKey=<exact plugin key>, and connectorSlug=<exact connector slug> so Wework can offer its user-initiated authorization card. Preserve the completed work and explain which operation is blocked. Do not read credential files, request passwords or tokens in chat, or run interactive login commands inside tools.
  • If the native authorization target includes a public instance, preserve that exact value as instance=<exact instance> in the authorization request and final auth-required message. Never infer an instance or substitute another host; the native flow validates its binding to the connector identity.
  • Platform-managed remote MCP authorization uses its native elicitation flow. Do not convert a remote MCP elicitation or a cloud-only connector error into a local authorization request.
  • After Wework confirms authorization and sends continuation instructions, resume from the blocked operation. Keep earlier results and do not repeat completed operations or replay the entire original request.
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. 2d ago First seen · 15 lines · 16 tokens per session scan A 14bc147cda0a

Subscribe to this mod's changes

connector-auth is a skill published in the GitHub repository wecode-ai/Wegent (886 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 437 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.

Claude CodeSecurityagentaichatbotcodexwework
Related

connector-auth compared with skills from other repositories

connector-auth next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
connector-authwecode-ai/WegentSkill886todayApache-2.0A16Claude Code
article-writernetease-youdao/LobsterAISkill6.2ktodayMITA62Claude Code, Codex
skin-creatornetease-youdao/LobsterAISkill6.2ktodayMITA48Claude Code, Codex
content-plannernetease-youdao/LobsterAISkill6.2ktodayMITA63Claude Code, Codex
skill-vetternetease-youdao/LobsterAISkill6.2ktodayMITA42Claude Code, Codex
stock-analyzernetease-youdao/LobsterAISkill6.2ktodayMITA53Claude Code, Codex
weathernetease-youdao/LobsterAISkill6.2ktodayMITA13Claude Code, Codex