AGENTS.md@configs/kimi-codeA

AGENTS.md@configs/kimi-code from jellydn/my-ai-tools is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add jellydn/my-ai-tools/configs/kimi-code/AGENTS.md@git:20260913.e2e25be

Pins git:20260913.e2e25be in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
jellydn/my-ai-tools
Path
configs/kimi-code/AGENTS.md
Versions recorded
5
Latest version
git:20260913.e2e25be, committed Sep 13, 2026
First version recorded
Jul 5, 2026
Size
2,378 bytes
Repository stars
128
License
MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ๐Ÿค– Kimi Code Agent Guidelines

## Communication

Use ASD-STE100 Simplified Technical English. Read a relevant `CONTEXT.md` when it governs terms or behavior you change.

## Session Management with tmux

Run dev servers, tests, and interactive CLIs inside tmux with the **current directory name as the session name** for easy debugging:

```bash
SESSION=$(basename "$PWD")
tmux new -d -s "$SESSION" 2>/dev/null || true

# Run dev server with portless if available, otherwise fallback to npm
if command -v portless &>/dev/null; then
    tmux send-keys -t "$SESSION" 'portless run npm run dev' Enter
else
    tmux send-keys -t "$SESSION" 'npm run dev' Enter
fi

tmux capture-pane -p -t "$SESSION" -S -20  # check output
```

## ๐Ÿ”ง AI Tool Guidelines

- Use the fff MCP tools for all file search operations instead of default tools.
- Use the sem MCP tools for semantic version control and git operations.
- When using bash commands for file/content search, prefer `fd` (fdfind) and `rg` (ripgrep) over standard `find` and `grep` for better performance and git-awareness.

## Token Efficiency

- Keep responses concise and actionable; lead with conclusions, file paths, and verification.
โ€ฆ

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jellydn/my-ai-tools/configs/kimi-code/AGENTS.md@sha256:0f3032272df6f5e6

The line at the top of this page pins the label git:20260913.e2e25be, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_aai7mti73eq63fmp.svg)](https://markdownregistry.com/a/art_aai7mti73eq63fmp)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 5, 2026 and Sep 13, 2026, about one every 18 days.

versioncommittedcommitsizeaudit
git:20260913.e2e25be latest2026-09-13 e2e25be 2,378 BA view ยท diff
git:20260805.03f07892026-08-05 03f0789 2,409 BA view ยท diff
git:20260730.6dd81c42026-07-30 6dd81c4 2,258 BA view ยท diff
git:20260708.5f081922026-07-08 5f08192 1,971 BA view ยท diff
git:20260705.f15f3002026-07-05 f15f300 2,220 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (2378 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jellydn/my-ai-tools ยท 128 stars ยท license MIT ยท pushed 2026-11-09 ยท branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_aai7mti73eq63fmp
GET https://markdownregistry.com/api/v1/resolve?ref=jellydn/my-ai-tools/configs/kimi-code/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/0f3032272df6f5e694f3376f92c66b46296ab2424652a6cf8bd3a83305e98e3a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md ยท AGENTS.md vs CLAUDE.md ยท which agent file does what.

More from jellydn/my-ai-tools

AGENTS.md AGENTS.md file
jellydn/my-ai-tools ยท AGENTS.md
git:20261022.251cb67 ยท audit A ยท 128 stars
AGENTS.md@configs/amp AGENTS.md file
jellydn/my-ai-tools ยท configs/amp/AGENTS.md
git:20260913.e2e25be ยท audit A ยท 128 stars
accountable-engineering SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/accountable-engineering/SKILL.md ยท Use explicit human checkpoints for architecture, security, rollout, or operational decisions.
git:20260913.e2e25be ยท audit A ยท 128 stars
adr SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/adr/SKILL.md ยท Record architecture decisions with ADRs โ€” captures why, alternatives considered, and consequences
git:20260814.d1987f5 ยท audit A ยท 128 stars
babysit-pr SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/babysit-pr/SKILL.md ยท Use when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.
v1.0.0 ยท audit A ยท 128 stars
blindspot-pass SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/blindspot-pass/SKILL.md ยท Inspect history and architecture for hidden constraints before risky cross-cutting changes.
git:20261007.163951e ยท audit A ยท 128 stars
capability-experiments SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/capability-experiments/SKILL.md ยท Build an interactive report or experiment when the user asks to explore model capabilities.
git:20260913.e2e25be ยท audit B ยท 128 stars
code-quality-review SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/code-quality-review/SKILL.md ยท Audit a diff for structural maintainability and unnecessary complexity.
git:20261104.30b60de ยท audit A ยท 128 stars
code-review SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/code-review/SKILL.md ยท Review a branch, PR, or worktree diff for repository conventions and stated intent.
git:20261006.f663cbc ยท audit A ยท 128 stars
codemap SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/codemap/SKILL.md ยท Create a seven-document architecture map when the user asks to map a codebase.
git:20261007.a4a976f ยท audit B ยท 128 stars
commit-atomic SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/commit-atomic/SKILL.md ยท Group staged changes into atomic commits with commitizen convention
git:20260814.d1987f5 ยท audit A ยท 128 stars
context-discovery SKILL.md skill
jellydn/my-ai-tools ยท configs/amp/plugins/my-ai-tools-skills/skills/context-discovery/SKILL.md ยท Use MCP tools to trace behavior that spans multiple modules or history sources.
git:20260913.e2e25be ยท audit A ยท 128 stars

Every file in jellydn/my-ai-tools

Browse by kind, by grade A, or by owner.