What is kimi-delegate?

A coordination workflow in which Codex plans and reviews a software task while Kimi Code carries out the implementation.

Use it to send implementation tasks to Kimi, inspect its changes, provide feedback, and verify the final result.

It separates planning and quality checks from code execution, with review steps before the work is accepted.

kimi-delegate — Skill for Claude Code and Codex by ximenchuifeng

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 ximenchuifeng/codex-kimi-bridge --skill kimi-delegate

Clone the repo

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ximenchuifeng/codex-kimi-bridge/kimi-delegate/github.svg)](https://agentmods.dev/skills/ximenchuifeng/codex-kimi-bridge/kimi-delegate)

Your own site

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

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 505 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00505
Opus 5.5	$0.00009	$0.00202
Sonnet 5.5	$0.00004	$0.00101
Haiku 4.5	$0.00002	$0.00051

Measured 2mo ago against content hash 113f5d4f435d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kimi-delegate 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.

plugins/kimi-delegate/skills/kimi-delegate/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kimi Delegate

Use this skill when the user wants Codex to act as planner, reviewer, and coordinator while Kimi Code performs implementation.

Rules

Codex owns spec, plan, review, verification, and final completion decisions.
Kimi owns implementation execution.
Do not implement code directly in Codex when the user has asked for Kimi execution.
Use kimi_delegate_task to send implementation tasks to Kimi.
Use kimi_get_handoff and kimi_get_diff before reviewing Kimi's work.
Use kimi_continue_task for review feedback until acceptance criteria pass.
Enable swarm mode only when the task has independent work items.
Do not auto-approve destructive commands.

Delegation Prompt

Every task sent to Kimi must include:

task
acceptance criteria
Codex plan
swarm split suggestion when useful
handoff requirements: a concrete final report plus committed and working-tree change evidence

Review Loop

Prepare or update the spec and implementation plan.
Delegate to Kimi.
Wait for Kimi to finish or block.
Gather handoff and diff.
Inspect both committedChanges and workingTreeChanges in the handoff or review package.
- A clean working tree does not prove Kimi made no changes; check committedChanges for commits and diffs.
- workingTreeChanges may include pre-existing user work listed in initialDirtyPaths.
- committedChanges.available: false means evidence is unavailable, not empty; use unavailableReason and direct git log/git diff when needed.
- The bridge persists Git baselines in a local store first, then falls back to session metadata. Check reviewWorkspace to see which worktree supplied the committed evidence.
- If reviewWorkspace differs from the session cwd, workingTreeChanges is marked review_workspace_mismatch instead of showing the wrong working tree.
- ambiguous_worktrees means multiple worktrees advanced from the baseline; inspect committedDiagnostics and review Git directly.
Review against acceptance criteria.
Send precise follow-up feedback to Kimi if review fails.
Independently verify before declaring completion.

Read the full file on GitHub · 47 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 · 47 lines · 22 tokens per session scan A 113f5d4f435d

Subscribe to this mod's changes

kimi-delegate is a skill published in the GitHub repository ximenchuifeng/codex-kimi-bridge (1 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 505 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 2026-09-01.

Building agents

kimi-delegate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kimi-delegateximenchuifeng/codex-kimi-bridge	Skill	1	3mo ago	MIT	A	22	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code