Borrowing it
Nothing to install: this file belongs to NomaDamas/katok. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NomaDamas/katok/main/AGENTS.mdgit clone --depth 1 https://github.com/NomaDamas/katokWrote 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/nomadamas/katok/agents-md)<a href="https://agentmods.dev/instructions/nomadamas/katok/agents-md"><img src="https://agentmods.dev/badge/instructions/nomadamas/katok/agents-md/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/instructions/nomadamas/katok/agents-md"><img src="https://agentmods.dev/badge/instructions/nomadamas/katok/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00832 | $0.00832 |
| Opus 5.5 | $0.00333 | $0.00333 |
| Sonnet 5.5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
katok 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- lazykatok AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kakao Memory Agent Instructions
These instructions apply to this repository and all child directories.
Project Intent
Kakao Memory is a local-first semantic memory and search layer for KakaoTalk conversations on macOS. Treat it as privacy-sensitive infrastructure, not a casual chat analyzer.
Architecture Guidelines
- Prefer source adapters over duplicating DB reverse engineering logic.
- The first source adapter should integrate with
kakaoclior thek-skillkakaotalk-machelper. - Keep ingestion, normalized archive, keyword search, semantic search, and skill wrapper as separable modules.
- Use stable message identifiers and incremental cursors so indexing can resume without rereading everything.
- Keep the agent skill thin: it should call the CLI and summarize results, not own indexing logic.
Development Guidelines
- Add tests before behavior changes.
- Use fixtures with synthetic chat data only.
- Do not create tests that depend on the user's real KakaoTalk installation or real local DB.
- Real KakaoTalk smoke tests may be manual-only and must avoid printing private content.
- Nothing derived from a real archive may be committed, including in documentation. This repository is public; the archive it reads is not. Avoiding private content in session output is not enough, because a finding made while looking at live data tends to get written down next to the rule it justified — a quoted message, a room name, a person's name or kinship term, a sample used because it was at hand. Skill files, comments, tests, and changelogs are all published. State the rule and drop the evidence: the observation that convinced you is for this conversation, not for the commit. Fixtures stay synthetic even when a real value would have been easier to paste.
- Keep README, CLI help, and privacy behavior aligned in the same change.
- Verify against the toolchain CI pins, and run every gate CI runs.
.github/workflows/ci.ymlpins the Rust version (matchingrust-versioninCargo.toml) and runs five gates:cargo fmt --all -- --check,cargo clippy --all-targets -- -D warnings,cargo test --all-targets,cargo publish --dry-run, andscripts/verify_release_config.py. A newer local toolchain passes work that CI rejects, because clippy retires and re-scopes lints between releases — socargo +<pinned> clippyis the check that counts. Running a subset and reporting it as green is the failure mode this exists to prevent.
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 · 65 lines · 832 tokens per session scan A 5f83c8b4d014
katok AGENTS.md is an instructions file published in the GitHub repository NomaDamas/katok (268 stars, last pushed 1mo ago), licensed MIT. It adds 832 tokens to every session, about $0.0033 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.