Borrowing it
Nothing to install: this file belongs to david-engelmann/maidan. 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/david-engelmann/maidan/main/CLAUDE.mdgit clone --depth 1 https://github.com/david-engelmann/maidanWrote 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/david-engelmann/maidan/claude-md)<a href="https://agentmods.dev/instructions/david-engelmann/maidan/claude-md"><img src="https://agentmods.dev/badge/instructions/david-engelmann/maidan/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/david-engelmann/maidan/claude-md"><img src="https://agentmods.dev/badge/instructions/david-engelmann/maidan/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 | $0.06278 | $0.06278 |
| Opus 5.5 | $0.02511 | $0.02511 |
| Sonnet 5.5 | $0.01256 | $0.01256 |
| Haiku 4.5 | $0.00628 | $0.00628 |
Grade A, and why
maidan 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 yesterday.
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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
If you are an AI agent or a human landing in this repo for the first time, read
this file end to end before doing anything else. It says how to work in the
codebase. The what lives in docs/: integrators start at
docs/Integration.md, contributors at
CONTRIBUTING.md and the doc index.
Commands
Everything runs from the repo root. Use the narrow forms while working; the full forms are what CI runs.
| Narrow (fast) | Full (what CI runs) | |
|---|---|---|
| Build | cargo build -p <crate> |
cargo build --workspace |
| Test | cargo test -p <crate> |
cargo nextest run --workspace --lib --bins --profile ci and cargo nextest run --workspace --tests --profile ci |
| Lint | cargo clippy -p <crate> --all-targets -- -D warnings |
cargo clippy --all-targets --workspace -- -D warnings, then the strict pass below |
| Format | cargo fmt --all |
cargo fmt --all --check |
| Run | MAIDAN_ALLOW_INSECURE_DEV_KEK=1 DATABASE_URL=sqlite::memory: MAIDAN_SESSION_SECRET=dev-session-secret-change-me-0123456789 cargo run --bin maidan-server |
— |
| Smoke | — | make smoke (Docker; brings the stack up and waits on its health checks) |
| Mutants | cargo mutants -p <crate> --shard 0/20 |
nightly: scripts/mutants.sh plan, then the shards (docs/Conventions.md, "Nightly mutation testing") |
| Fuzz | cd fuzz && cargo +nightly fuzz run <target> -- -max_total_time=60 |
nightly, in fuzz/, for each target that cargo +nightly fuzz list prints: cargo +nightly fuzz run --target x86_64-unknown-linux-gnu <target> corpus/<target> seeds/<target> -- -dict=json.dict -max_total_time=300 (seeds/<target> only where it exists; docs/Conventions.md, "Nightly fuzzing") |
| Docs site | — | mdbook-mermaid install book && bash book/sync-docs.sh && mdbook build book && ./scripts/check-docs-presentation.sh |
The server refuses to start without a content key: set MAIDAN_CONTENT_KEK, or
MAIDAN_ALLOW_INSECURE_DEV_KEK=1 for local work only.
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.
- yesterday Changed · +7 lines · +126 tokens per session bdb70a7279be
- 9d ago Changed · +17 tokens per session f720aae3845a
- 11d ago Changed · +1 lines · -16 tokens per session 55f68e007366
- 12d ago Changed · +3 lines · +59 tokens per session 7a5c59697314
- 14d ago Changed · +6 lines · +102 tokens per session 426e6b66c7f3
- 17d ago Changed · +3 lines · +68 tokens per session 202b6bb75bf8
- 19d ago Changed · +10 lines · +191 tokens per session 2945e5881919
- 20d ago Changed · -2 tokens per session 01067f129220
- 22d ago Changed · +70 lines · +1,426 tokens per session e4492fcb9c00
- 23d ago First seen · 297 lines · 4,307 tokens per session scan A 09460621762b
maidan CLAUDE.md is an instructions file published in the GitHub repository david-engelmann/maidan (7 stars, last pushed yesterday), licensed MIT. It adds 6,278 tokens to every session, about $0.0251 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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.