Borrowing it
Nothing to install: this file belongs to CAREEMER/appflowy-mcp. 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/CAREEMER/appflowy-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/CAREEMER/appflowy-mcpWrote 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/careemer/appflowy-mcp/agents-md)<a href="https://agentmods.dev/instructions/careemer/appflowy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/careemer/appflowy-mcp/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/careemer/appflowy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/careemer/appflowy-mcp/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 | $0.00668 | $0.00668 |
| Opus 5.5 | $0.00267 | $0.00267 |
| Sonnet 5.5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
appflowy-mcp 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 2mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents (and humans) working on appflowy-mcp.
Project layout
src/appflowy_mcp/— the package.config.py— settings + token/scope parsing from env and config files.appflowy.py— async AppFlowy REST/collab client.access.py— token-scoped access control over workspaces and page subtrees.blocks.py— Yjs/CRDT document decoding and block editing helpers.server.py— FastMCP tools + entrypoint.
tests/— the test suite (one file per source module).
Commands
uv sync # install runtime + dev dependencies
uv run pytest # run all tests with the coverage gate
uv run ruff check # lint
Definition of Done
A change is done only when all of the following hold:
-
100% test coverage. Line and branch coverage of
appflowy_mcpmust be 100%. This is enforced by--cov-fail-under=100inpyproject.toml; never lower it. New code ships with the tests that cover it. Genuinely unreachable lines (optional-import fallbacks, defensiveraises after exhaustive loops) are excluded with an explicit# pragma: no coverand a one-line reason — not by relaxing the threshold. -
One test = one small piece of behaviour. Each test exercises a single function or branch and asserts one thing. Do not bundle unrelated assertions into a "kitchen sink" test. Prefer many small tests over a few large ones.
-
Clear test names. A test's name states what it verifies, in the form
test_<unit>_<behaviour>— e.g.test_scope_parse_empty_raises,test_request_reauthenticates_once_on_401. Reading the name alone should tell you what broke when it fails. -
No superfluous comments. Tests should read as self-explanatory. Comments are only for non-obvious setup (e.g. why a CRDT document is shaped a certain way), never to restate what the code plainly does.
-
Lint passes.
uv run ruff checkis clean. -
The pipeline gates on tests. The Docker image build
needs: test(.github/workflows/docker.yml); a failing test or a coverage drop must block the image from being built. Do not work around this gate.
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.
- 2mo ago First seen · 61 lines · 668 tokens per session scan A 3b070f2f7115
appflowy-mcp AGENTS.md is an instructions file published in the GitHub repository CAREEMER/appflowy-mcp (8 stars, last pushed 3mo ago), licensed MIT. It adds 668 tokens to every session, about $0.0027 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 2026-08-31.
appflowy-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| appflowy-mcp AGENTS.mdCAREEMER/appflowy-mcp | Instructions file | 8 | 3mo ago | MIT | A | 668 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |