Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/alanadson/yard/agents-mdgit clone --depth 1 https://github.com/alanadson/yardWhat 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 | $0.03222 | $0.03222 |
| Opus 5 | $0.01611 | $0.01611 |
| Sonnet 5 | $0.00644 | $0.00644 |
| Haiku 4.5 | $0.00322 | $0.00322 |
Grade A, and why
yard 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how work gets done in this repository
This applies to every agent (Claude Code, Codex, OpenCode…) and to every human.
Read it in full before your first Edit. The architecture specs live in
docs/; the test discipline in detail, with the examples
that already exist in the code, is in
docs/specs/06-tdd.md.
The rule
No line of production code lands here without a test that failed first. TypeScript, Rust, it makes no difference. You write the test, watch it fail for the right reason, and only then write the code that makes it pass.
This is not an ideal to chase when there is time left over — it is the shape of the work. A task that is "done" with no new test is a task not delivered, and reporting it as done is reporting wrong.
Why here, specifically: this app orchestrates real processes (ConPTY, Job
Objects, SQLite, git worktrees) and exposes a contract to external agents (the
yard CLI). Almost everything that breaks here breaks silently — an orphan
wire in layoutJson, a leftover node.exe, a pipe name that changed. None of
it shows up on screen. It only shows up in the test.
0. Thirty seconds before you touch anything
Run the baseline and confirm it is green. If it is already red, that is the first task — do not pile new work on top of a broken suite.
npm test # vitest — today: 151 files, 1824 tests, ~8 s
npm run typecheck # tsc --noEmit
cd src-tauri; cargo test --lib # Rust — pty::engine_tests spawns a real PowerShell
From the repository root, without changing directory:
cargo test --manifest-path src-tauri/Cargo.toml --lib
1. The cycle, step by step
RED — write the test first
- Say in one sentence, in the voice of behaviour, what is going to change: "closing the tab also deletes the card's role and routines". That sentence becomes the test name.
- Write the test against the API you wish you had, even if it does not exist yet. That is how you discover the good signature before spending an hour on the bad one.
- Run just that test and look at the failure:
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 First seen · 277 lines · 3,222 tokens per session scan A e981c235d41a
yard AGENTS.md is an instructions file published in the GitHub repository alanadson/yard (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,222 tokens to every session, about $0.0161 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 2026-08-31.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.