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/tinygodsdev/bitext-word-alignment/agents-mdgit clone --depth 1 https://github.com/tinygodsdev/bitext-word-alignmentWhat 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 | $0.00774 | $0.00774 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
bitext-word-alignment 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
This file defines stable, project-agnostic instructions for AI agents working in this repository. Keep this file short and universal. Do not add project-specific documentation, plans, temporary notes, or implementation details here.
Project knowledge
Treat AGENTS.md as read-only operating guidance. Do not edit it or use it as project memory.
Language
Reply to the user in the language they used in their message. Reading skills, instructions, or other files does not change this: the user's message language decides the reply language, regardless of the language of any files or skills you read while working.
Tasks
When you need to search or find project tasks, issues, tickets, etc., address to @PROJECT.md file for specific instructions. Respect the task management system described there.
Architecture
- Use the simplest architecture that keeps the code easy to understand, test, and change.
- Separate responsibilities when they have different reasons to change.
- Avoid adding layers, patterns, or abstractions before they solve a real problem in the codebase.
- Keep business/domain logic away from framework, UI, transport, storage, and infrastructure details when practical.
Comments
- Code should be self-explanatory.
- Use clear, descriptive variable and function names.
- Structure code so its intent is obvious.
- Use comments only when they add useful context that is not obvious from the code.
- Keep comments concise and to the point.
- Comments in code files should always be in English.
- If code needs a long comment to be understood, refactor it first.
Error handling
- Errors should be visible. Avoid silent and hidden errors.
- Errors should be specific. Avoid wrapping lots of logic in a single try-catch block (or other error handling mechanism).
- Avoid fallback code unless it is an explicit requirement of the task. Fail fast to prevent hiding broken functionality.
- Do not handle multiple input formats unless it is required by the task. For example, if some variable should be "https://example.com" (with domain) don't handle "example.com" as well, unless it is explicitly required by the task. Handle unexpected input as an error, unless the task required to support multiple formats.
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 · 69 lines · 774 tokens per session scan A 34ca34ee7dbf
bitext-word-alignment AGENTS.md is an instructions file published in the GitHub repository tinygodsdev/bitext-word-alignment (5 stars, last pushed 10d ago), licensed MIT. It adds 774 tokens to every session, about $0.0039 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.