What is codex-kimi-bridge AGENTS.md?

Project instructions for a bridge that lets Codex plan and review work while Kimi Code implements it through a local server. They define the preferred handoff and review process.

Use them when coordinating Kimi implementation, reviewing its returned work package, checking the local plugin state, or following the documented delegation workflow.

They clarify which agent should write the plan, implement changes, run checks, and review the results, reducing duplicated or unauthorized implementation work.

How ximenchuifeng/codex-kimi-bridge configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ximenchuifeng/codex-kimi-bridge. 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/ximenchuifeng/codex-kimi-bridge/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ximenchuifeng/codex-kimi-bridge

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ximenchuifeng/codex-kimi-bridge/agents-md/github.svg)](https://agentmods.dev/instructions/ximenchuifeng/codex-kimi-bridge/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ximenchuifeng/codex-kimi-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/ximenchuifeng/codex-kimi-bridge/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ximenchuifeng/codex-kimi-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/ximenchuifeng/codex-kimi-bridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,444 This file is loaded in full into every session.

When invoked 2,444 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02444	$0.02444
Opus 5.5	$0.00978	$0.00978
Sonnet 5.5	$0.00489	$0.00489
Haiku 4.5	$0.00244	$0.00244

Measured 2mo ago against content hash e5c99ff5d53f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

codex-kimi-bridge AGENTS.md 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 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

Do not commit real tokens. `.mcp.json` keeps `KIMI_SERVER_TOKEN` empty.

AGENTS.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project

codex-kimi-bridge is a local Codex plugin plus MCP bridge. Its purpose is to let Codex act as planner/reviewer while Kimi Code performs implementation through the local Kimi server.

Default workspace:

/Users/ximenchuifeng/Coding/codex-kimi-bridge

Related Kimi Code source checkout:

/Users/ximenchuifeng/Coding/BigWave/kimi-code

Collaboration Rule

The preferred workflow is:

Codex writes the spec and plan.
Codex delegates implementation to Kimi through kimi_delegate_and_wait.
Kimi changes code and runs verification.
Codex reviews the embedded reviewPackage, independently verifies, and either accepts or sends follow-up feedback.

Do not manually implement feature work in Codex when the user says execution should happen in Kimi. Codex may still do small local maintenance tasks when explicitly asked, such as reinstalling the plugin, committing already-reviewed work, or writing this file.

Reusable prompt templates live in:

docs/prompts/kimi-delegate-workflow.md

Current Plugin State

Local marketplace:

/Users/ximenchuifeng/Coding/codex-kimi-bridge/.agents/plugins/marketplace.json

Plugin id:

kimi-delegate@codex-kimi-bridge-local

MCP config:

plugins/kimi-delegate/.mcp.json

The plugin MCP server currently launches:

node ./mcp/server.mjs

After code changes that affect MCP tools or plugin config, run:

pnpm build
codex plugin add kimi-delegate@codex-kimi-bridge-local

Then open a new Codex thread or restart Codex if the tool list does not refresh.

plugins/kimi-delegate/mcp/server.mjs is a tracked generated artifact.
Source changes affecting MCP runtime require pnpm build and committing the regenerated bundle.
Fresh clone installation does not require pnpm because the bundle is tracked.
Development reinstalls use update_plugin_cachebuster.py; release manifests use plain semantic versions.

Kimi Server

Default server:

Read the full file on GitHub · 222 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.

2mo ago First seen · 222 lines · 2,444 tokens per session scan B e5c99ff5d53f

Subscribe to this mod's changes

codex-kimi-bridge AGENTS.md is an instructions file published in the GitHub repository ximenchuifeng/codex-kimi-bridge (1 stars, last pushed 3mo ago), licensed MIT. It adds 2,444 tokens to every session, about $0.0098 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Building agents

codex-kimi-bridge AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-kimi-bridge AGENTS.mdximenchuifeng/codex-kimi-bridge	Instructions file	1	3mo ago	MIT	B	2,444	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

codex-kimi-bridge: Instructions file for Codex