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/microsoft/intelligent-terminal/rust-localizationgit clone --depth 1 https://github.com/microsoft/intelligent-terminalWhat 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 | $0.03172 | $0.03172 |
| Opus 5 | $0.01586 | $0.01586 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade A, and why
intelligent-terminal rust-localization.instructions.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 2d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Localization Instructions for Rust WTA (YAML Locale Files)
Overview
The WTA (Windows Terminal Agent) Rust project uses rust-i18n v3 with YAML locale files. Translations are compiled into the binary at build time — there is no runtime file loading.
File structure
wta/locales/
├── en-US.yml ← source of truth (developers edit this first)
├── zh-CN.yml ← Simplified Chinese
├── zh-TW.yml ← Traditional Chinese
├── ja-JP.yml ← Japanese
├── ... (locale set MUST match Terminal's .resw locale folders)
Important: The set of
.ymllocale files must always match the set of.reswlocale folders insrc/cascadia/TerminalApp/Resources/. If Terminal adds or removes a locale, WTA must follow. Never hardcode the count — discover it dynamically from the.reswfolders.
File format
-
One YAML file per locale, filename = locale code (e.g.,
de-DE.yml) -
Flat dot-separated keys (no nested objects)
-
UTF-8 encoding (no BOM needed — unlike
.resw) -
Strings wrapped in double quotes
The en-US.yml Source File
en-US.yml is the source of truth. All other locale files translate from it.
When adding new strings:
- Add the key + English value to
en-US.yml - Add
{Locked}comments for non-translatable tokens (see Non-Translatable Token Rules below) - Translate to all other locale files following Terminology Alignment rules (see Step 1: Determine the target locale set below)
- Rebuild (
cargo build) — translations are baked in at compile time
Non-Translatable Token Rules
Since YAML has no structured comment system like .resw, we use # comments with {Locked} syntax borrowed from .resw. There are three scope levels:
File-level (top of file, applies to everything)
Place at the very top of the file, before any section headers. These define constraints that apply to every string in the file.
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.
- 2d ago First seen · 226 lines · 3,172 tokens per session scan A 591ff48cd897
intelligent-terminal rust-localization.instructions.md is an instructions file published in the GitHub repository microsoft/intelligent-terminal (1,895 stars, last pushed 2d ago), licensed MIT. It adds 3,172 tokens to every session, about $0.0159 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 2026-08-30.
Other instructions, from other repositories
coddy-agent AGENTS.md
Instructions for coddy-project/coddy-agent, covering agent notes for coddy, repository navigation, builds, pre-commit gate and documentation contract.
kiro-discord-bot AGENTS.md
Instructions for nczz/kiro-discord-bot, covering agents.md — kiro-discord-bot agent contract, source-of-truth map, non-negotiable principles, architecture boundaries and discord output and i18n.
coddy-agent CLAUDE.md
Instructions for coddy-project/coddy-agent, a project described as: General-purpose agent in one static Go binary. ReAct loop, ACP server for IDEs, OpenAI-compatible REST API with embedded web UI, Telegram gateway, cron scheduler, long-term memory, context compaction, rules, skills, MCP. Distroless-ready, works with…
mini-swe-agent copilot-instructions.md
Instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
Octop AGENTS.md
Instructions for TencentCloud/Octop, covering agents.md, 1. collaboration principles, think before writing, simplicity first and surgical edits.