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/jyjeanne/rustyspec/copilot-instructionsgit clone --depth 1 https://github.com/jyjeanne/rustyspecWrote 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/jyjeanne/rustyspec/copilot-instructions)<a href="https://agentmods.dev/instructions/jyjeanne/rustyspec/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jyjeanne/rustyspec/copilot-instructions.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 | $0.00840 | $0.00840 |
| Opus 5 | $0.00420 | $0.00420 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
rustyspec copilot-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 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RustySpec Project Guidelines
What This Project Is
RustySpec is a Rust CLI tool (rustyspec) implementing Specification-Driven Development (SDD) — it transforms feature descriptions into structured specs, plans, tasks, and test scaffolds, then orchestrates AI agents to implement them.
See docs/ARCHITECTURE.md for full system architecture and data flows.
Build and Test
# Build
cargo build --release
# Test (uses assert_cmd + tempfile for CLI integration tests)
cargo test
# Run locally
cargo run -- [subcommand]
Rust edition: 2024. No Makefile or justfile — Cargo is the sole build tool.
Architecture
The codebase has a strict layered separation:
| Layer | Location | Rule |
|---|---|---|
| CLI | src/cli/ |
No business logic — thin handlers only; delegate to core/agents/templates |
| Domain | src/core/ |
Pure logic, no CLI imports — library-ready |
| Agent integration | src/agents/ |
21 AI agents, data-driven config, CLI invocation with fallback to handoff |
| Templating | src/templates/ |
Tera rendering; 4-layer resolution (see below) |
| Config | src/config/ |
TOML-based; RootConfig + PipelineConfig |
| Extensions/Presets | src/extensions/, src/presets/ |
CRUD + cross-platform hook execution |
Each src/cli/ file maps 1-to-1 to a subcommand. Never add business logic there.
Key Conventions
Errors: Use RustySpecError (src/core/errors.rs) with thiserror. Every error variant must include a fix field with a human-actionable suggestion. Use anyhow::Result in fallible functions.
CLI parsing: Clap derive macros (#[derive(Parser)]). Global --debug flag lives on the root Cli struct.
Serialization: serde with #[derive(Serialize, Deserialize)] for all config/manifest types.
Embedded templates: Use include_str!() to embed templates from templates/ into the binary. Template resolution priority:
1. .rustyspec/templates/overrides/ ← project-level tweaks (highest)
2. .rustyspec/presets/<id>/templates/
3. .rustyspec/extensions/<id>/templates/
4. Binary-embedded defaults ← fallback
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 · 76 lines · 840 tokens per session scan A 6b8dfd51492f
rustyspec copilot-instructions.md is an instructions file published in the GitHub repository jyjeanne/rustyspec (5 stars, last pushed 4mo ago), licensed MIT. It adds 840 tokens to every session, about $0.0042 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
skills-hub AGENTS.md
Instructions for liuxingqitd/skills-hub, covering agents.md, commands, project overview, architecture and 应用结构.
deepsteve CLAUDE.md
Instructions for deepsteve/deepsteve, covering deepsteve, development workflow, restart the daemon after making changes, check if running, and read logs and stop the daemon.
deepsteve AGENTS.md
Instructions for deepsteve/deepsteve, covering agents.md - agent guidelines for deepsteve, project overview, running the application, development and production.
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).
pixcode AGENTS.md
AGENTS.md instructions for alicomert/pixcode, covering agents.md, commands, smoke tests (manual, no npm script), architecture boundaries and agent adapters.
Warden-AI copilot-instructions.md
Copilot instructions for rynald0cst0ltziam/Warden-AI, covering warden — context governance and verification layer, session start (important — do this first), layer 1: before starting work — context selection, layer 2: during work — tool output pruning and enforcement hooks (automatic).