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/stefaniuk/loadout/rustgit clone --depth 1 https://github.com/stefaniuk/loadoutWhat 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 | $0.04442 | $0.04442 |
| Opus 5 | $0.02221 | $0.02221 |
| Sonnet 5 | $0.00888 | $0.00888 |
| Haiku 4.5 | $0.00444 | $0.00444 |
Grade A, and why
loadout 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Engineering Instructions 🦀
These instructions define Rust-specific engineering patterns beyond what the Rust Book, compiler, and Clippy already enforce.
They must remain applicable to:
- CLI applications and system tools
- Web services and APIs (Actix, Axum, Rocket)
- Libraries and shared crates
- Async applications (Tokio, async-std)
- Embedded and systems programming
- WebAssembly and Tauri backends
This file does not restate Rust fundamentals (ownership, borrowing, Result, Option, ? operator). Those are assumed knowledge. It covers decision criteria, thresholds, and patterns that require human judgement.
They are non-negotiable unless an exception is explicitly documented (with rationale and expiry) in an ADR/decision record.
Identifier scheme. Every normative rule carries a unique tag in the form [RS-<prefix>-NNN], where the prefix maps to the containing section (for example QR for Quick Reference, DEC for Decisions, ASY for Async, API for API Design). Use these identifiers when referencing, planning, or validating requirements.
0. Quick reference (apply first) 🧠
This section exists so humans and AI assistants can reliably apply the most important rules even when context is tight.
- [RS-QR-001] Function size: split functions exceeding ~50 lines or 3 levels of nesting ([RS-STR-001]).
- [RS-QR-002] Clone acceptance:
clone()is acceptable for smallCopy-like types, startup paths, or when profiler shows no impact ([RS-DEC-003]). - [RS-QR-003] No blocking in async: never call blocking IO or hold locks across
.await([RS-ASY-001], [RS-ASY-003]). - [RS-QR-004] Cancellation safety: document whether async functions are cancellation-safe ([RS-ASY-005]).
- [RS-QR-005] Error types: libraries return typed errors; binaries may use
anyhow([RS-ERR-001]). - [RS-QR-006] Unsafe review: all
unsafeblocks require a// SAFETY:comment and dedicated review ([RS-SAF-001]). - [RS-QR-007] No warnings in CI:
#![deny(warnings)]or equivalent in CI; fix, don't suppress ([RS-QG-001]). - [RS-QR-008] Feature flag hygiene: test with
--no-default-featuresand--all-features([RS-ORG-004]). - [RS-QR-009] Structured logging: use
tracingfor structured logs; follow the baseline field requirements ([RS-OBS-001]). - [RS-QR-010] CLI contract: exit codes follow
0/1/2contract; stdout for results, stderr for diagnostics ([RS-CLI-001]).
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 · 287 lines · 4,442 tokens per session scan A 9dac85bdff4b
loadout rust.instructions.md is an instructions file published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 3d ago), licensed MIT. It adds 4,442 tokens to every session, about $0.0222 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
apm cli.instructions.md
CLI Design Guidelines for visual output, styling, and user experience standards.
apm integrators.instructions.md
Architecture rules for file-level integrators (BaseIntegrator pattern).
apm cicd.instructions.md
CI/CD Pipeline configuration for PyInstaller binary packaging and release workflow.
apm encoding.instructions.md
Cross-platform encoding rules — keep all source and CLI output within printable ASCII.
spec-driven-steroids AGENTS.md
Instructions for lindoelio/spec-driven-steroids, covering agents.md, project identity, technology stack, essential commands and agent constraints.
featherspec constitution.instructions.md
FeatherSpec constitution editing rules (thin loader).