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/andr-ca/agentharness/rustgit clone --depth 1 https://github.com/andr-ca/agentharnessWrote 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/andr-ca/agentharness/rust)<a href="https://agentmods.dev/instructions/andr-ca/agentharness/rust"><img src="https://agentmods.dev/badge/instructions/andr-ca/agentharness/rust.svg" alt="Measured on agentmods" 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 | $0.00909 | $0.00909 |
| Opus 5 | $0.00454 | $0.00454 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
agentharness 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 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated from languages/rust/CONVENTIONS.md by
tools/generate-copilot-instructions.sh
(https://github.com/andr-ca/agentharness) — do not hand-edit; regenerate
instead. Only applied by Copilot when editing a file matching
*.rs.
Rust Conventions & Best Practices
Naming (snake_case for functions/variables/modules, PascalCase for
types/traits/enum-variants, SCREAMING_SNAKE_CASE for consts/statics),
module layout, and the borrow-checker mechanics are all standard Rust
community convention — see the
Rust API Guidelines and
RFC 430 naming
for the parts not worth restating here. rustfmt (formatting) and
clippy (lints) are the non-negotiable baseline — run both in CI; don't
hand-argue formatting. Below are the places this repo makes an actual
decision.
unwrap()/expect() is a rigor-tier decision, not a habit
.unwrap() and .expect() turn a None/Err into a panic. That's fine
at the Prototype tier and in tests, but at the Internal and Production
tiers library and request-path code must propagate errors with ?
instead — a panic in a request handler takes down more than the request.
Reserve expect() for genuine invariants that cannot fail, and when you
use it, make the message state why it can't fail, not what failed:
// Good: the message documents the invariant.
let port = env::var("PORT").expect("PORT is set by the launcher before exec");
// Bad in Internal/Production code: propagate instead.
let config = load_config()?; // not load_config().unwrap()
See .github/CODING_GUIDELINES.md's
rigor tiers for which tier applies.
Error types: thiserror for libraries, anyhow for binaries
- Libraries expose a concrete, matchable error enum
(
#[derive(thiserror::Error)]) so callers can handle specific cases — don't leakBox<dyn Error>across a public API. - Binaries / application code can use
anyhow::Resultwith.context()to add human-readable context at each boundary, since the top-level handler only needs to report, not match.
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 · 98 lines · 909 tokens per session scan A 01be7d495aba
agentharness rust.instructions.md is an instructions file published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 909 tokens to every session, about $0.0045 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 2026-09-03.
Other instructions, from other repositories
diri AGENTS.md
AGENTS.md instructions for cristicretu/diri, covering diri repository instructions, scope, completed remote architecture baseline, rust workspace map and remote architecture invariants.
clave-cli CLAUDE.md
Claude Code instructions for grabrick/clave-cli, covering claude.md — навигатор по проекту clave, 0. что такое clave, 1. жёсткие правила общения и авторства, 2. тулчейн (иначе cargo: command not found) and 3. гейт: без него ничего не отгружается.
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.