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/kunagent/kun/agents-mdgit clone --depth 1 https://github.com/KunAgent/KunWhat 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 | $0.02603 | $0.02603 |
| Opus 5 | $0.01301 | $0.01301 |
| Sonnet 5 | $0.00521 | $0.00521 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
Kun AGENTS.md scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Startup debugging should not rely on a single port check. Combine the real process path, `open -n <Kun.app>`, `lsof -iTCP:18787,18788,18899`, `curl http://127.0.0.1:18899/health`, and `~/Library/Application Support/Kun The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 129 lines · 2,603 tokens per session scan A afec75d18731
Kun AGENTS.md is an instructions file published in the GitHub repository KunAgent/Kun (6,261 stars, last pushed 2d ago), with no licence file. It adds 2,603 tokens to every session, about $0.0130 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Lody AGENTS.md
Instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
ChatCCC AGENTS.md
Instructions for wzj998/ChatCCC, covering 协作原则（核心）, 开发注意点 and 日志位置.
Lody CLAUDE.md
Instructions for LodyAI/Lody, a project described as: Share coding agents with your team on phone and desktop.
pie AGENTS.md
Instructions for dineshdb/pie, covering testing, architecture, i'm an idiot, simplification and scope.
ChatCCC CLAUDE.md
Instructions for wzj998/ChatCCC, covering 协作原则（核心）, 开发注意点 and 日志位置.