Borrowing it
Nothing to install: this file belongs to yorkie-team/yorkie. 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/yorkie-team/yorkie/main/CLAUDE.mdgit clone --depth 1 https://github.com/yorkie-team/yorkieWrote 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/yorkie-team/yorkie/claude-md)<a href="https://agentmods.dev/instructions/yorkie-team/yorkie/claude-md"><img src="https://agentmods.dev/badge/instructions/yorkie-team/yorkie/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.
<a href="https://agentmods.dev/instructions/yorkie-team/yorkie/claude-md"><img src="https://agentmods.dev/badge/instructions/yorkie-team/yorkie/claude-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 | $0.01385 | $0.01385 |
| Opus 5.5 | $0.00554 | $0.00554 |
| Sonnet 5.5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
yorkie 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yorkie — CRDT-based Collaboration Server
Go server providing document synchronization via CRDTs with MongoDB or in-memory storage.
Architecture docs live under docs/design/; tasks under @docs/tasks/README.md.
Commands
make tools # Install dev tools (run periodically)
make build # Build binary to bin/yorkie
make fmt # gofmt
make lint # golangci-lint
make verify # lint + licence headers + go fix + unit tests — the commit gate
make modernize # Apply go fix under every build tag (fixes verify-modernize)
make proto # Regenerate protobuf via buf
make test # Integration tests (-tags integration, MongoDB required)
make test-complex # Long-running complex tests (-tags complex)
make bench # Benchmarks (-tags bench)
make coverage # Integration test coverage (MongoDB required)
go test ./... # Unit-only tests (no build tag, no DB)
# Integration test environment
docker compose -f build/docker/docker-compose.yml up --build -d
Commit Messages
Per CONTRIBUTING.md: subject ≤70 chars (what changed), blank line,
body wrapped at 80 chars (why). bash scripts/setup.sh, once per clone,
installs the hooks that check this and the gates in step 2 below.
Skip leadership write when active leader exists
Follower nodes unconditionally attempted FindOneAndUpdate with
is_leader=true every renewal cycle (default 5s). With N nodes this
produced N-1 duplicate key errors per cycle on the
is_leader_true_unique partial index.
In shell, use multiple -m flags or $'...' for real newlines —
not \n inside "...".
Key Architecture
- Three-layer data model: JSON-like (user-facing) → CRDT (conflict resolution) → Common (shared primitives).
- Entry point:
cmd/yorkie/. - Generated code:
api/yorkie/v1/(protobuf viamake proto). - Design docs:
docs/design/— always consult before changing architecture; keep updated when behavior changes.
Pitfalls
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.
- 25d ago Changed · +4 lines · +83 tokens per session b4873e559f25
- 1mo ago Changed · +3 lines · +70 tokens per session f8c1dbe8d313
- 1mo ago Changed · +4 lines · +79 tokens per session 3941d7103b5b
- 1mo ago Changed · +7 lines · +114 tokens per session 998e759e6324
- 2mo ago First seen · 98 lines · 1,039 tokens per session scan A 887a030a5279
yorkie CLAUDE.md is an instructions file published in the GitHub repository yorkie-team/yorkie (930 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,385 tokens to every session, about $0.0055 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.