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 agentmods add instructions/luhfilho/kimi-plugin-cross-platform/agents-mdgit 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/instructions/luhfilho/kimi-plugin-cross-platform/agents-md)<a href="https://agentmods.dev/instructions/luhfilho/kimi-plugin-cross-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/luhfilho/kimi-plugin-cross-platform/agents-md.svg" alt="Measured on agentmods" 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 | $0.01577 | $0.01577 |
| Opus 5 | $0.00788 | $0.00788 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
kimi-plugin-cross-platform AGENTS.md 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- kimi-plugin-cross-platform CLAUDE.md — 97% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance when working with code in this repository.
What this is
kimi-plugin-cross-platform — a cross-platform kit that lets three host CLIs (Claude Code, Codex CLI, Antigravity CLI) delegate work to the Kimi CLI (Moonshot AI) for code review, "rescue" tasks, and background jobs. Pure Node.js (ESM, >=20), npm workspaces, no build step, no runtime dependencies.
Commands
npm test # all tests (node --test via custom runner)
npm run test:unit # unit tests only (tests/unit/)
npm run test:integration # integration tests only (tests/integration/)
npm run test:adapters # adapter tests (tests/adapters/)
# Run a single test FILE
node --test tests/unit/wire-client.test.mjs
# Run a single test CASE within a file (pattern matches the it()/test() name)
node --test --test-name-pattern="renders review findings" tests/unit/render.test.mjs
node scripts/test-e2e.mjs # end-to-end suite (uses fake-kimi fixture)
node scripts/install.mjs --all # install adapters into ~/.claude, ~/.codex, ~/.antigravity
node scripts/install.mjs --dry-run # preview install actions without writing
- Lint/format are NOT configured —
npm run lint/npm run formatare placeholderechos. Do not assume a linter exists. - CI (
.github/workflows/ci.yml) runstest:unit,test:integration, andtest:adapterson Node 20 and 22. It does not run e2e.
Do not "simplify" the test runner
scripts/run-tests.mjs is a hand-rolled runner that walks directories and passes explicit test file paths to node --test. It exists specifically to work around shell glob-expansion differences across platforms and to avoid executing helper fixtures as top-level tests — replacing it with node --test tests/**/*.mjs will break CI on some shells. Leave it in place.
Architecture
Two layers. The split is the most important thing to understand:
core/src/ ← the ONLY runtime logic. Host-agnostic. Change behavior here.
adapters/<host>/ ← thin wrappers (commands, skills, agents, prompts). No business logic.
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.
- 5d ago First seen · 83 lines · 1,577 tokens per session scan A bec4e4c3a4fa
kimi-plugin-cross-platform AGENTS.md is an instructions file published in the GitHub repository luhfilho/kimi-plugin-cross-platform (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,577 tokens to every session, about $0.0079 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
ai-driven-development AGENTS.md
AGENTS.md instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.
llm-engineering-skills CLAUDE.md
Claude Code instructions for itsmostafa/llm-engineering-skills, covering claude.md, repository purpose, repository files, skill structure and skill.md requirements.
TechShorts AGENTS.md
AGENTS.md instructions for LarsenCodeLabs/TechShorts, covering repository structure, core product constraints, development and verification, security and configuration and solana/anchor protocol rules.
cross-cli-handshake AGENTS.md
AGENTS.md instructions for jpbaking/cross-cli-handshake: Follow the Portable Agent Authoring guides for harness discovery and persistent instructions.
IDE-Adapter CLAUDE.md
Instructions for godstale/IDE-Adapter, covering claude.md, commands, architecture, adding a new handler and protocol rules.
ai-driven-development CLAUDE.md
Claude Code instructions for CodeAlive-AI/ai-driven-development, a project described as: Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.