agentmods.dev

config-manager-connect

config-manager-connect is a skill for Claude Code, Codex from slash9494/ai-config-sync-manager. It costs 18 tokens per session (394 once invoked), scanned A, original, MIT.

A connection guide for linking Codex with the open-source AI Config Sync Manager command-line tool. It describes how the bundled command initializes the sync manager's user configuration and connects supported hosts.

In plain words
What is it for?
Use it to connect Codex or another supported AI host through AI Config Sync Manager, view command help, and handle a missing installation.
Why use it?
It provides the required command, environment setting, help behavior, and fallback when the bundled tool is unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 47repo 3d ago A scan SkillSpector: pass 18 tokens original MIT

Good fit Use it to connect Codex or another supported AI host through AI Config Sync Manager, view command help, and handle a missing installation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/slash9494/ai-config-sync-manager/config-manager-connect
View source ↗ slash9494/ai-config-sync-manager
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 slash9494/ai-config-sync-manager --skill config-manager-connect
Clone the repo
git clone --depth 1 https://github.com/slash9494/ai-config-sync-manager

Made for: Claude Code, Codex.

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 config-manager-connect

README.md
[![agentmods](https://agentmods.dev/badge/skills/slash9494/ai-config-sync-manager/config-manager-connect/github.svg)](https://agentmods.dev/skills/slash9494/ai-config-sync-manager/config-manager-connect)
Your own site
<a href="https://agentmods.dev/skills/slash9494/ai-config-sync-manager/config-manager-connect"><img src="https://agentmods.dev/badge/skills/slash9494/ai-config-sync-manager/config-manager-connect/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 config-manager-connect

Your own site · 80×15
<a href="https://agentmods.dev/skills/slash9494/ai-config-sync-manager/config-manager-connect"><img src="https://agentmods.dev/badge/skills/slash9494/ai-config-sync-manager/config-manager-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 394 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00018 $0.00394
Opus 5.5 $0.00007 $0.00158
Sonnet 5.5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00039

Measured 2mo ago against content hash 936bbe48d0ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

config-manager-connect 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 2mo 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.

integrations/codex-plugin/skills/config-manager-connect/SKILL.md · 28 lines

What it actually says

Config Manager Connect

Use this skill when the user asks to connect Codex, Claude, or another supported host through AI Config Sync Manager.

Behavior

  • If the user passes -h / --help (or asks for usage/help), run ... connect --help and print the CLI output as-is — do not execute the connect flow.
  • Resolve the bundled CLI from the Codex plugin root: AI_CONFIG_SYNC_HOST=codex "$HOME/.agents/plugins/ai-config-sync-manager/bin/ai-config-sync" connect. The launcher resolves the runtime via AI_CONFIG_SYNC_ROOT (dev override) → PATH ai-config-sync → npm exec fallback.
  • Always export AI_CONFIG_SYNC_HOST=codex before invoking the CLI from this skill so the default sync direction is codex -> claude.
  • The connect command initializes the user config root at $HOME/.ai-config-sync-manager and creates $HOME/.ai-config-sync-manager/status-ignore.json when missing.
  • Do not edit Codex, Claude, skills, commands, MCP, permissions, or hooks directly from this skill.
  • If the bundled CLI is unavailable, report that the user must npm install -g ai-config-sync-manager (or run npm link from the repo) and re-run connect.
  • Prefer explicit user confirmation before installing, registering, or writing anything outside the current plugin flow.
  • Preserve the OSS purpose: this plugin is a thin open-source bridge to the bundled CLI, not a proprietary sync service.

Safety

  • Treat host permissions, hooks, and custom commands as manual-review areas.
  • When the CLI proposes changes, show the summary and ask for confirmation before continuing.
  • If the CLI reports backups, mention their location before any apply step proceeds.
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. 2mo ago First seen · 28 lines · 18 tokens per session scan A 936bbe48d0ad

Subscribe to this mod's changes

config-manager-connect is a skill published in the GitHub repository slash9494/ai-config-sync-manager (47 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 394 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 2026-08-30.

Building agents
Related

config-manager-connect compared with skills from other repositories

config-manager-connect next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
config-manager-connectslash9494/ai-config-sync-managerSkill473d agoMITA18Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k2d agoMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill315k6d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code