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.
git clone --depth 1 https://github.com/luhfilho/kimi-plugin-cross-platformWrote 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/plugins/luhfilho/kimi-plugin-cross-platform/kimi)<a href="https://agentmods.dev/plugins/luhfilho/kimi-plugin-cross-platform/kimi"><img src="https://agentmods.dev/badge/plugins/luhfilho/kimi-plugin-cross-platform/kimi/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/plugins/luhfilho/kimi-plugin-cross-platform/kimi"><img src="https://agentmods.dev/badge/plugins/luhfilho/kimi-plugin-cross-platform/kimi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kimi 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 1mo 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.
What it actually says
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "kimi",
"version": "0.2.0",
"description": "Delegate work to Kimi CLI (Moonshot AI) for code review, rescue tasks, and Kimi Code implementation."
}
What it installs
The manifest is a name and a version. 3 skills, 9 commands, 2 agents, 2 hooks travel with it, and installing the plugin installs all of them — 115 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill kimi-cli-runtime A 0 tokens
- Skill kimi-prompting A 0 tokens
- Skill kimi-result-handling A 0 tokens
- Command adversarial-review A 15 tokens
- Command review A 12 tokens
- Command result A 10 tokens
- Command code A 13 tokens
- Command implement A 8 tokens
- Command rescue A 10 tokens
- Command setup A 9 tokens
- Command cancel A 8 tokens
- Command status A 9 tokens
- Agent kimi-code A 10 tokens
- Agent kimi-rescue A 11 tokens
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
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.
- 1mo ago First seen · 7 lines scan A 65eb7e25b3d0
kimi is a plugin published in the GitHub repository luhfilho/kimi-plugin-cross-platform (1 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
graph-it-live
Dependency, call-graph, impact, and architecture analysis for codebases.
dumb-boss
The anti-sycophant reviewer. Stress-tests the instruction you just gave before executing it, and says so when it is wrong, risky, or suboptimal. Flags in one line, then does the work anyway. Stops only for what cannot be undone.
8eyes
Failure-aware multi-agent code review with 8 hook-enforced roles. Works on Claude Code, Copilot CLI, and Codex CLI.
agent-rack
Run claude, codex, opencode, Antigravity, or any CLI coding agent as MCP tools from Claude Code, plus structured read-only code review.
slop-review
Native diff review window (Monaco + Glimpse) for AI coding agents. Browse changes since the merge-base with your base branch (or last commit / uncommitted), leave inline + file-level + overall comments on the slop, and have the agent address each item.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.