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 skills add FeiZhuLulu/Agent-Bridge --skill add-coordinatorgit clone --depth 1 https://github.com/FeiZhuLulu/Agent-BridgeWrote 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/feizhululu/agent-bridge/add-coordinator)<a href="https://agentmods.dev/skills/feizhululu/agent-bridge/add-coordinator"><img src="https://agentmods.dev/badge/skills/feizhululu/agent-bridge/add-coordinator/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.
<a href="https://agentmods.dev/skills/feizhululu/agent-bridge/add-coordinator"><img src="https://agentmods.dev/badge/skills/feizhululu/agent-bridge/add-coordinator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.01951 |
| Opus 5 | $0.00037 | $0.00975 |
| Sonnet 5 | $0.00015 | $0.00390 |
| Haiku 4.5 | $0.00007 | $0.00195 |
Grade B, and why
add-coordinator 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Codex | `~/.codex/config.toml` `[mcp_servers.*]` | `~/.codex/skills` | `tool_timeout_sec` (seconds) | Clears MCP child env; list `env_vars`. | How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a coordinator host to Agent Bridge
This is not add-worker.
- add-worker connects a new execution CLI to Registry / adapters /
agents.toml. - add-coordinator proves a new host can drive the existing workers through the same MCP tools.
Do not add an adapter, a worker block, or a new dispatch protocol for a coordinator. Do not use GUI automation. Do not treat "the config file was written" as an end-to-end pass.
Before writing anything
Answer every item below from the host's current official docs and, when possible, its source. Record units (seconds vs milliseconds) and scope (user vs project).
- stdio MCP config shape, scopes, and precedence. User file vs project file. Whether a native config and a
.agents/mcp.jsonfallback merge or replace each other. Whether the settings UI paste format differs from the on-disk file. - Whether MCP server
instructionsreach the model. Handshake text is one channel; if the host hides it, the skill andORCHESTRATION.mdmust still be discoverable. - AGENTS.md / rules loading and size limits. Path, walk order, concatenation, and any byte/token cap.
- Skill directories. Native user dir, project dir, generic
~/.agents/skills, plugin/marketplace paths, and whether discovery is automatic. - MCP startup timeout and tool-call timeout, with units. Recommend a value that leaves room for
wait_taskdefault 180 s (Bridge recommends 600 s / 600000 ms). Document the host default and the short-poll fallback when the default is too short or unknown. - MCP tool permission / approval. How to pre-allow only Agent Bridge tools without turning the whole host into always-approve. Note which keys are user-scoped and must not go in a project example.
- Environment inheritance and executable PATH. Does the host clear the MCP child env (Codex does)? Can it resolve a PowerShell function, or must
commandbe a real executable absolute path? - Can this product also be a Worker? If yes, a Worker that inherits the user's Agent Bridge MCP config will start a nested Bridge. Prove the server-side gate: nested
list_agentsshowsruntime_context=workeranddispatch_enabled=false; nesteddispatch_task(evenuser_requested=true) returnsnested dispatch is disabled. - Real closed loop on the live host:
list_agents→dispatch_task→wait_task→get_result→ samesession_idcontinue →end_session. Verify the file on disk yourself. A timeout is not failure. - Separate automation from human steps. Unit tests and a project-level config fixture are automation. Opening a GUI host and sending one prompt is human. Never call the latter "E2E passed".
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.
- 9d ago First seen · 76 lines · 75 tokens per session scan B 4818bf6d4688
add-coordinator is a skill published in the GitHub repository FeiZhuLulu/Agent-Bridge (34 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,951 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…