llms.txtA

llms.txt from kimyx0207/meta_kim is an llms.txt file: plain text a project publishes for AI models to read.

Install it, pinned
mdr add kimyx0207/meta_kim/llms.txt@git:20261003.02b13ba

Pins git:20261003.02b13ba in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
llms.txt file
Repository
kimyx0207/meta_kim
Path
llms.txt
Versions recorded
3
Latest version
git:20261003.02b13ba, committed Oct 3, 2026
First version recorded
Jun 5, 2026
Size
3,401 bytes
Repository stars
290
License
Apache-2.0

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

# Meta_Kim

Meta_Kim is a general agent governance framework: it turns user goals into evidence-backed decisions, capability discovery, bounded ownership, orchestration, outcome verification, and writeback across domains.

It coordinates research, operations, learning, writing, software and other tasks through a repeatable spine:

Critical -> Fetch -> Thinking -> Execution -> Review -> Meta-Review -> Verification -> Evolution

## Core Idea

Runtime agents provide execution capabilities. Meta_Kim governs how they serve the current user's outcome:

- clarify the real intent before execution
- search available capabilities before picking an owner
- compare feasible routes under the user's constraints and state the limits of the recommendation
- route work to bounded agents, skills, scripts, MCP providers, or runtime tools
- review and verify results with artifacts
- distinguish structural checks, routing, native invocation and actual task outcomes
- write back useful lessons only after approval

## Start Here

- Project overview: README.md
- Chinese overview: README.zh-CN.md
- Maintainer guide: AGENTS.md
- Claude Code guide: CLAUDE.md
- First-run proof: examples/first-run/README.md
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kimyx0207/meta_kim/llms.txt@sha256:a6349f9124d7127d

The line at the top of this page pins the label git:20261003.02b13ba, 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_gnx33sc4b5bivsqc.svg)](https://markdownregistry.com/a/art_gnx33sc4b5bivsqc)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in kimyx0207/meta_kim/llms.txt since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of llms.txt from somewhere else? Ask it: where did my llms.txt come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 3 versions of this file, between Jun 5, 2026 and Oct 3, 2026, about one every 60 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261003.02b13ba latest2026-10-03 02b13ba 3,401 BA view · diff
git:20260619.cdb82562026-06-19 cdb8256 3,146 BA view · diff
git:20260605.3dc04f32026-06-05 3dc04f3 3,004 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (3401 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

kimyx0207/meta_kim · 290 stars · license Apache-2.0 · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gnx33sc4b5bivsqc
GET https://markdownregistry.com/api/v1/resolve?ref=kimyx0207/meta_kim/llms.txt
GET https://markdownregistry.com/api/v1/blob/a6349f9124d7127dbfe911ae2529605f741f86f5382235105f7fd00ccb82fa80

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 add an llms.txt file to a website · which agent file does what.

More from kimyx0207/meta_kim

AGENTS.md AGENTS.md file
kimyx0207/meta_kim · AGENTS.md
git:20261115.5431daf · audit A · 290 stars
CLAUDE.md CLAUDE.md file
kimyx0207/meta_kim · CLAUDE.md
git:20261115.5431daf · audit A · 290 stars
save-progress SKILL.md skill
kimyx0207/meta_kim · canonical/runtime-assets/claude/commands/save-progress/SKILL.md · Save current project task progress to local task state file for cross-session continuity. Use when the user asks to…
git:20260612.208934c · audit B · 290 stars
meta-theory SKILL.md skill
kimyx0207/meta_kim · canonical/skills/meta-theory/SKILL.md · Meta_Kim executable governance dispatcher. It classifies the run, loads only needed references, preserves foundational…
v3.0.0 · audit A · 290 stars
same-set-reusable-flow-for-project-file-inventor SKILL.md skill
kimyx0207/meta_kim · canonical/skills/same-set-reusable-flow-for-project-file-inventor/SKILL.md · Reusable Meta_Kim file inventory classification flow. It helps separate durable sources, generated evidence, runtime…
v0.1.0 · audit A · 290 stars

Every file in kimyx0207/meta_kim

Other files named llms.txt

llms.txt llms.txt file
tt-a1i/archify · llms.txt
git:20261115.889982e · audit A · 97,305 stars
llms.txt llms.txt file
garrytan/gbrain · llms.txt
git:20261104.dea361e · audit A · 33,088 stars
llms.txt llms.txt file
othmanadi/planning-with-files · llms.txt
git:20260917.2fbbd77 · audit A · 28,141 stars
llms.txt llms.txt file
hkustdial/supervisor-skills · llms.txt
git:20260716.1bb65a3 · audit A · 12,931 stars
llms.txt llms.txt file
tw93/kami · llms.txt
git:20261009.3d11cf5 · audit B · 12,545 stars
llms.txt llms.txt file
deanchensj/jiangshan-map · llms.txt
git:20261116.29f0656 · audit A · 7,776 stars
llms.txt llms.txt file
dramaclaw/dramaclaw · llms.txt
git:20260630.14354c0 · audit A · 7,714 stars
llms.txt llms.txt file
tw93/waza · llms.txt
git:20260907.2ae9e48 · audit A · 7,590 stars

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