Borrowing it
Nothing to install: this file belongs to olk/architecture-pattern-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/olk/architecture-pattern-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/olk/architecture-pattern-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/olk/architecture-pattern-mcp/agents-md)<a href="https://agentmods.dev/instructions/olk/architecture-pattern-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/olk/architecture-pattern-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/olk/architecture-pattern-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/olk/architecture-pattern-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 | $0.00812 | $0.00812 |
| Opus 5 | $0.00406 | $0.00406 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
architecture-pattern-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 today.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules — architecture-pattern-mcp
Static typing (MANDATORY)
src/is mypy strict.uv run mypy --strictMUST exit 0 before finishing any task.- Clear all zuban LSP diagnostics (mypy mode) in files you touch. Known, accepted
divergence: zuban reports a few errors stock mypy does not (e.g. some
pipeline.pyslice/misc findings) and vice versa; stock mypy is authoritative for CI — fix both sets where possible, never introduce zuban-only constructs. - Annotate every function signature; parameterize all generics (
dict[str, X], notdict;re.Match[str], notMatch). - No bare
Anyin public signatures. - NO mypy plugins (zuban cannot run them). Pydantic: use
Field(default=...)keyword form, never positional defaults;default_factorygets a named, return-annotated factory function. # type: ignore[<code>]ONLY where third-party stubs are provably wrong; always with a justification comment. No baretype: ignore, no blanket ignores.- New third-party imports: prefer typed libs /
tests-*stubs (types-*); otherwise add a per-module override in[tool.mypy]with a comment. - Scope:
src/only (tests/,examples/currently unchecked).
Quality gates
make check-lint(ruff),make check-static-typing(mypy),make test-unit,make check-deadcode,make check-depcheck— all must pass before task completion (make check-allruns the four check-* gates in one go).- Runtime behavior of existing code must not change while fixing type errors;
tests/unit/is the behavioral oracle.
Verification program
- Changing job/pipeline control flow: update the matching
.fizzmodel inverify/fizz/in the same PR, prove it withmake verify-fizz; CI re-checks all specs on every push regardless of what the agent did; every assertion must kill at least one spec-garden mutant and appear in theverify/fizz/README.mdledger. - Every
.fizzalways/always eventuallyassertion must kill at least one spec-garden mutant or carry a# spec-explains:justification — vacuous assertions are rejected. - The executable layers (L1 unit tests, L2 Hypothesis oracles, L3 gardens,
L4 FizzBee, L6 DST) are the verification authority; a change to the decision
modules (
src/text_validation.py,src/design_normalization.py) must keeptests/unit/andtests/verification/green. - L3 scope changes (any edit to
[tool.mutmut]inpyproject.toml) must update theverify/mutmut-scope.mdledger row in the same PR. The Python garden (tests/verification/gardens/bug_garden.py) now declares SIX bug classes;make test-mutationsenforces a ratchet against the committedverify/mutmut-baseline.json(new survivors and kill-ratio drops fail the gate; deliberate refresh viamake regen-mutmut-baseline; acknowledged equivalents go toverify/mutmut-equivalents.md). The mutation-scope modules and their oracles are listed there;tests/unit/internals tests (test_text_validation_internals.py,test_design_normalization_internals.py) are the direct kill oracles for the decision-engine primitives.
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.
- today Changed · +11 lines · +198 tokens per session cf19bd9b0556
- yesterday Changed · +15 lines · +230 tokens per session a8938e901981
- 5d ago First seen · 26 lines · 384 tokens per session scan A c31f5f6a5276
architecture-pattern-mcp AGENTS.md is an instructions file published in the GitHub repository olk/architecture-pattern-mcp (0 stars, last pushed today), licensed MIT. It adds 812 tokens to every session, about $0.0041 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 2026-09-07.
Other instructions, from other repositories
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.
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.
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.
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).
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 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).