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 skills/ryo-ebata/cc-audit/cli-architecturenpx skills add ryo-ebata/cc-audit --skill cli-architecturegit clone --depth 1 https://github.com/ryo-ebata/cc-auditWrote 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/skills/ryo-ebata/cc-audit/cli-architecture)<a href="https://agentmods.dev/skills/ryo-ebata/cc-audit/cli-architecture"><img src="https://agentmods.dev/badge/skills/ryo-ebata/cc-audit/cli-architecture.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 | $0.00041 | $0.02747 |
| Opus 5 | $0.00020 | $0.01373 |
| Sonnet 5 | $0.00008 | $0.00549 |
| Haiku 4.5 | $0.00004 | $0.00275 |
Grade A, and why
cli-architecture 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 5d 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 — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Architecture Best Practices
Reference tools: Biome, OxcLint, ripgrep, fd
Core Design Principles
1. Zero-Config by Default
User experience priority:
1. Works out of the box with sensible defaults
2. Configuration is optional enhancement
3. Explicit overrides when needed
// BAD: Requires configuration to work
let config = Config::load("config.yaml")?; // Fails if missing
// GOOD: Sensible defaults, optional config
let config = Config::load_or_default("config.yaml");
2. Modular Composability (Oxc Pattern)
Each component works independently or together:
┌─────────────────────────────────────────────┐
│ CLI │
├─────────────────────────────────────────────┤
│ ┌─────────┐ ┌─────────┐ ┌─────────────┐ │
│ │ Scanner │ │ Reporter│ │ Config │ │
│ └────┬────┘ └────┬────┘ └──────┬──────┘ │
│ │ │ │ │
├───────┴───────────┴─────────────┴───────────┤
│ Core Engine │
├─────────────────────────────────────────────┤
│ ┌────────┐ ┌────────┐ ┌────────┐ │
│ │ Parser │ │ Rules │ │ Types │ │
│ └────────┘ └────────┘ └────────┘ │
└─────────────────────────────────────────────┘
3. Performance First
- Parallel by default: Use
rayonfor file processing - Streaming output: Don't buffer entire results
- Lazy evaluation: Load resources on demand
- Memory efficiency: Process files without loading all into memory
Crate Organization (Workspace Pattern)
Recommended Structure
my-tool/
├── Cargo.toml # Workspace root
├── crates/
│ ├── my_tool/ # Main library (pub API)
│ ├── my_tool_cli/ # CLI binary (thin wrapper)
│ ├── my_tool_parser/ # Parser implementation
│ ├── my_tool_rules/ # Rule definitions
│ ├── my_tool_config/ # Configuration handling
│ └── my_tool_reporter/ # Output formatters
├── xtask/ # Development tasks
└── tests/ # Integration tests
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.
- 5d ago First seen · 457 lines · 41 tokens per session scan A 9042121cb475
cli-architecture is a skill published in the GitHub repository ryo-ebata/cc-audit (24 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,747 once invoked, about $0.0002 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 skills, from other repositories
rust-code-style
Write idiomatic, well-structured Rust for Wassette — single-responsibility design, anyhow error handling, Arc/Mutex for shared state, and the required formatting and linting with cargo +nightly fmt, cargo clippy, and cargo machete. Use when adding or refactoring Rust code in this repository.
update-keyboard-shortcuts
Audits and synchronizes keyboard shortcuts across docs/keyboardshortcuts.md, crates/regenerator2000-tui/src/ui/dialogkeyboardshortcut.rs, crates/regenerator2000-tui/src/ui/menu.rs, and the view files (viewdisassembly.rs, viewhexdump.rs, viewcharset.rs, viewbitmap.rs, viewblocks.rs, viewsprites.rs).
coding
Skill "coding" from ricardoquesada/regenerator2000, covering 6502 disassembler expert skills, core context, technical requirements, 1. 6502 logic and 2. rust performance & safety.
rust-modern-style
Apply rag-rat's Rust style when writing or reviewing Rust: current stable idioms, module-qualified free functions and constants, explicit persistence contracts, and narrow APIs.
add-module
Add a new crate to the bioprism workspace implementing a blueprint section, including registering it, choosing dependencies without creating cycles, and the honesty conventions every crate must follow. Use when starting a new module, when asked to cover an uncovered blueprint section, or when setting up work for a…
verify-crate
Verify a bioprism crate is genuinely green — tests passing and clippy at zero warnings — and recognise the environment failures that masquerade as test failures. Use before claiming a crate is done, after landing an agent's work, when a test count looks wrong or lower than expected, or when cargo test reports a…