What is krimto CLAUDE.md?

Contributor instructions for Krimto, an open-source team memory layer that stores shared agent knowledge in Git files and provides search and access controls.

Use them when changing Krimto storage, search, permissions, its MCP server, data structures, or concurrency behavior.

They give coding agents project rules, including which changes need planning, tests-first development, and full verification after every change.

How krimto-labs/krimto configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to krimto-labs/krimto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/krimto-labs/krimto/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/krimto-labs/krimto

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/krimto-labs/krimto/claude-md/github.svg)](https://agentmods.dev/instructions/krimto-labs/krimto/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/krimto-labs/krimto/claude-md"><img src="https://agentmods.dev/badge/instructions/krimto-labs/krimto/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/krimto-labs/krimto/claude-md"><img src="https://agentmods.dev/badge/instructions/krimto-labs/krimto/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 707 This file is loaded in full into every session.

When invoked 707 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00707	$0.00707
Opus 5	$0.00353	$0.00353
Sonnet 5	$0.00141	$0.00141
Haiku 4.5	$0.00071	$0.00071

Measured 12d ago against content hash 6993d011d4cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

krimto CLAUDE.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 12d 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.

CLAUDE.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Krimto — Contributor and Development Guidelines

If you are an AI agent

Read this section before doing anything. Krimto is an open-source team memory layer for AI coding agents. Quality matters more than quantity. Slop PRs will be closed.

Before opening any PR:

Identify which subsystem your change touches: storage, index, access, retrieval, or the MCP server.
Changes to the data schema, the MCP tool surface, the retrieval algorithm, access control, or the concurrency model are load-bearing — design them in Plan Mode first.
Write tests first (TDD). Run the full verification suite below; everything must pass.

What this project is

Open-source team memory layer for AI agents. Three layers:

Storage — markdown files in git (the source of truth)
Index — SQLite + sqlite-vec for hybrid retrieval (BM25 + vector)
Access — an API server enforces the user → team → org hierarchy

Defining properties: markdown-files-in-git as the storage layer, and user → team → org hierarchy as the primary primitive. Krimto is Apache-2.0 licensed and stays that way.

Code conventions

TypeScript, strict mode (tsconfig strict: true)
camelCase for variables, PascalCase for types
Functions over classes unless state requires otherwise
No any — use unknown and narrow
pnpm for all dependency and script management

Required verification (after every change)

pnpm typecheck — passes
pnpm lint — passes
pnpm test — relevant unit tests pass
pnpm test:integration — the five-step end-to-end acceptance test passes

Architecture rules — never violate

All writes go through the API server
Folder paths are the data model, not access control
The server enforces access via .krimto/members.yaml
Never bypass the SQLite write coordinator
Frontmatter id is immutable and server-created only
Timestamps are server-generated only
No automatic fact extraction — facts are written only on an explicit krimto_write

Read the full file on GitHub · 80 lines

Changes

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.

12d ago First seen · 80 lines · 707 tokens per session scan A 6993d011d4cd

Subscribe to this mod's changes

krimto CLAUDE.md is an instructions file published in the GitHub repository krimto-labs/krimto (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 707 tokens to every session, about $0.0035 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.

Claude Code Memory and context agent-memory ai-agents ai-memory coding-agents cursor

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

krimto: Instructions file for Claude Code