Borrowing it
Nothing to install: this file belongs to WojcikMM/spec-development-protocol. 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/WojcikMM/spec-development-protocol/main/AGENTS.mdgit clone --depth 1 https://github.com/WojcikMM/spec-development-protocolWrote 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/wojcikmm/spec-development-protocol/agents-md)<a href="https://agentmods.dev/instructions/wojcikmm/spec-development-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/wojcikmm/spec-development-protocol/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/wojcikmm/spec-development-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/wojcikmm/spec-development-protocol/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 | $0.03591 | $0.03591 |
| Opus 5.5 | $0.01436 | $0.01436 |
| Sonnet 5.5 | $0.00718 | $0.00718 |
| Haiku 4.5 | $0.00359 | $0.00359 |
Grade A, and why
spec-development-protocol 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 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 — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Files matching **/*
Global Coding Standards
Apply these standards proportionally to the project type and the stack defined
in TECH.md. Process and orchestration rules live in
sdlc-process.instructions.md.
Code Quality
- Prefer small, focused functions and intent-revealing names.
- Avoid speculative abstractions and unnecessary indirection.
- Remove meaningful duplication without forcing unrelated code into a shared abstraction.
- Prefer guard clauses and clear control flow over deep nesting.
- Keep side effects explicit and isolate external boundaries.
- Match architectural complexity to the problem.
Architecture
- Separate domain/application concerns from infrastructure where the distinction improves testability or changeability.
- Keep dependencies directed toward stable contracts.
- Prefer composition over inheritance.
- Reuse established project patterns before introducing a new one.
- A simple change does not require a new architecture layer or ADR.
Error Handling
- Validate external input at system boundaries.
- Represent expected failures explicitly rather than using broad exceptions for control flow.
- Surface actionable messages without exposing secrets, stack traces, or internal details.
- Distinguish transient, permanent, and programmer failures.
- Do not swallow errors or convert failures into success-shaped results.
Testing
- Test observable behavior rather than private implementation details.
- Cover business-critical happy paths, error paths, and material edge cases.
- Use unit, integration, and end-to-end tests where each provides independent confidence; do not require every test layer for every change.
- Keep tests isolated and deterministic where practical.
- Use clear Arrange-Act-Assert structure when it improves readability.
- Prefer one behavioral focus per test; multiple assertions are appropriate when they jointly verify one outcome.
- Do not skip, delete, or weaken a failing test merely to pass a 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.
- yesterday Changed · +162 lines · -774 tokens per session scan C → A a09e41880c3c
- 1mo ago First seen · 298 lines · 4,365 tokens per session scan C 00d38de52e94
spec-development-protocol AGENTS.md is an instructions file published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed yesterday), licensed MIT. It adds 3,591 tokens to every session, about $0.0144 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).
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.