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/rustgit 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 | $0.00435 | $0.00435 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
intelligent-terminal rust.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 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust conventions
Follow the existing crate's architecture and style before introducing a new pattern or dependency.
Implementation
- Prefer clear ownership and borrowing over cloning or unnecessary allocation.
- Use domain types and enums to make invalid states difficult to represent.
- Accept
&stror borrowed values when ownership is not required. - Keep iterators lazy when that improves clarity; use direct loops when they are easier to read.
- Keep async work non-blocking. Move blocking filesystem or process work to the crate's established blocking boundary.
- Avoid
unsafe. When it is required, minimize its scope and document the safety invariant. - Do not add abstraction, traits, builders, or dependencies without a concrete need in the changed code.
Errors
- Return
Resultfor recoverable failures and add context at I/O, process, parsing, and protocol boundaries. - Use the crate's existing error type and conventions; do not introduce a new error-handling dependency solely for a local change.
- Avoid
unwrap,expect, and panics in production paths unless an invariant is both local and demonstrably impossible to violate. - Do not silently discard errors. Log, propagate, or explicitly document why an error is intentionally ignored.
Documentation and tests
- Comment invariants, non-obvious concurrency, and compatibility constraints; do not narrate straightforward code.
- Add focused tests for behavior changes and regressions. Keep unit tests near the code unless the crate already uses an integration-test boundary.
- Do not require every private item to have documentation or every change to introduce a new abstraction.
Validation
- Run
cargo fmtfor changed Rust code. - Run the smallest relevant tests while iterating, then the crate's required test command.
- Run Clippy only when the crate already uses it or the task requires it; do not perform unrelated cleanup.
- Keep builds warning-free under the repository's configured toolchain.
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 · 53 lines · 435 tokens per session scan A 600788084432
intelligent-terminal rust.instructions.md is an instructions file published in the GitHub repository microsoft/intelligent-terminal (1,895 stars, last pushed yesterday), licensed MIT. It adds 435 tokens to every session, about $0.0022 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.
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.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.