Borrowing it
Nothing to install: this file belongs to agagniere/speky. 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/agagniere/speky/master/AGENTS.mdgit clone --depth 1 https://github.com/agagniere/spekyWrote 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/agagniere/speky/agents-md)<a href="https://agentmods.dev/instructions/agagniere/speky/agents-md"><img src="https://agentmods.dev/badge/instructions/agagniere/speky/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/agagniere/speky/agents-md"><img src="https://agentmods.dev/badge/instructions/agagniere/speky/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 | $0.01266 | $0.01266 |
| Opus 5.5 | $0.00506 | $0.00506 |
| Sonnet 5.5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
speky 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
Project Overview
Speky is a Python tool for writing project specifications (requirements and tests) in YAML or TOML, version-controlled alongside code. It generates static HTML (via Sphinx/MyST) and PDFs (via Typst), and exposes specs to LLM agents via an MCP server.
Commands
Setup:
uv sync
Run all tests:
uv run pytest --import-mode importlib --quiet
Run a single test:
uv run pytest --import-mode importlib tests/test_mcp_server.py::TestInitialization::test_initialize -v
Format and lint:
uv run --dev ruff format python tests
uv run --dev ruff check python tests
uv run --dev ruff check --fix python tests
Validate YAML specs:
make -C specs check
Generate Markdown and HTML from specs:
uv run speky specs/speky.yaml --output-folder markdown
uv run --with furo,sphinx-design,sphinx-copybutton,myst-parser sphinx-build -M html markdown output --conf-dir .
Sphinx's conf.py must set project, include 'substitution' in myst_enable_extensions, and set myst_substitutions = {'project': project}.
Architecture
The project has two Python packages under python/:
speky — CLI tool
main.py— Argument parsing and orchestrationspecification.py— Loads YAML/TOML files andkind: projectmanifests, resolves cross-references, scans source code forspeky:<project>#<ID>tags, computes test-plan coveragemodels.py—Requirement,Test,Comment,Manifest,SourceLinkConfigdata modelsscanner.py— Tree-sitter based scanner extracting code references from Python/Go/Rust/Bash sourcesgenerators/markdown.py— MyST Markdown outpututils.py,log_formatter.py— Field-import helpers and CLI log formattingassets/— Defaultlogging.yamlconfig andspeky.csscopied into the generated Markdown folder
speky_mcp — MCP server
Exposes specs over JSON-RPC 2.0 to LLM clients (e.g., Claude).
server.py— Startup, initialization, request dispatchtools.py— Tool implementations (search, get, list operations)protocol.py— JSON-RPC error types
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.
- 1mo ago First seen · 100 lines · 1,266 tokens per session scan A 6e8f7dd418e3
speky AGENTS.md is an instructions file published in the GitHub repository agagniere/speky (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,266 tokens to every session, about $0.0051 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.