What is rust-bash AGENTS.md?

Repository-specific instructions for AI coding agents working on the rust-bash project. They define which documentation is authoritative and the required steps and execution rules for tasks.

Use them when implementing or reviewing any change in the rust-bash repository, especially when consulting its guidebook or working through its project milestones.

They reduce the chance of an agent changing the wrong subsystem, skipping required project guidance, or using forbidden file operations. They also make task completion and documentation updates more consistent.

rust-bash AGENTS.md — Instructions file by shantanugoel

Install

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.

agentmods

npx agentmods add instructions/shantanugoel/rust-bash/agents-md

Clone the repo

git clone --depth 1 https://github.com/shantanugoel/rust-bash

Made for: Codex, OpenCode.

Per session 469 This file is loaded in full into every session.

When invoked 469 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00469	$0.00469
Opus 5	$0.00234	$0.00234
Sonnet 5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 3d ago against content hash 76675d2ee952, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-bash 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 3d 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.

AGENTS.md · 33 lines

What it actually says

AGENTS.md

Minimal operating guide for AI agents in this repo.

Canonical spec

Single source of truth: docs/guidebook/ (see guidebook README)

Steps to do for any task

Agents MUST follow these steps for every task:

Read the relevant chapter(s) in docs/guidebook/.
Map the task to the milestones in Chapter 10.
Understand how the task relates to other subsystems before implementing.
Implement without over-engineering. Prioritize readability and maintainability. The project currently has a low user base and MUST NOT implement any backward compatibility or legacy handling.
Review your own changes thoroughly to fix any issues found and verify the original goal was met.
If any oracle agent is available to you, ask it to review your changes as well thoroughly in parallel and check which comments make sense, and fix those.
Check if the changes done in the task need an update to README.md or docs/guidebook and make the changes if so including, but not limited to, marking the completed items appropriately in the plan.

Agent execution rules

All file operations in rust-bash go through VirtualFs — never use std::fs in command or interpreter code.
No std::process::Command — all commands are in-process Rust implementations.
Reuse existing types/traits before adding new abstractions.
Keep changes incremental and test-gated.
Run cargo fmt, cargo clippy -- -D warnings and cargo test on touched areas before finishing.
Whenever any code changes are made, make sure all builds (main package, node and wasm packages, all examples, all tests, etc) build and test fine
File, function, and test names should describe behavior, not planning phases.
Avoid clippy allow directives — fix the underlying issue instead.
If requirements are unclear or conflicting, ask the user instead of guessing.
When choosing between design approaches, present pros/cons and ask the user.
Whenever adding any dependency crate, make sure we are using the latest version of it.
NEVER commit any changes unless explcitly asked for by the user.

Changes

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.

3d ago First seen · 33 lines · 469 tokens per session scan A 76675d2ee952

Subscribe to this mod's changes

rust-bash AGENTS.md is an instructions file published in the GitHub repository shantanugoel/rust-bash (27 stars, last pushed 5mo ago), licensed MIT. It adds 469 tokens to every session, about $0.0023 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.

agents ai ai-agents bash shell

rust-bash AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

AGENTS.md

Canonical spec

Steps to do for any task

Agent execution rules

What this file has done since we first saw it

Other instructions, from other repositories

dotfiles AGENTS.md

dotfiles AGENTS.md

claude-wrapper CLAUDE.md

tools AGENTS.md

shellnium CLAUDE.md

bash-lsp CLAUDE.md