claw-code-parity
```markdown
What this skill does
```markdown
---
name: claw-code-parity
description: Rust port parity work for the claw-code project, providing a harness runtime with agent tool orchestration capabilities
triggers:
- "help me with claw-code parity"
- "rust port for claw-code"
- "set up claw code harness"
- "how do I use the claw-code rust port"
- "claw-code parity commands"
- "run parity audit for claw-code"
- "claw-code agent harness rust"
- "port manifest for claw-code"
---
# Claw Code Parity (Rust Port)
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
**claw-code-parity** is a temporary Rust port parity workspace for the [claw-code](https://github.com/instructkr/claw-code) project. It provides a faster, memory-safe harness runtime that mirrors the architectural patterns of Claude Code's agent harness — including tool wiring, command orchestration, and agent workflow management. This repo bridges the gap while the main `claw-code` repository completes its migration.
---
## What It Does
- Implements the core **agent harness runtime** in Rust for performance and memory safety
- Mirrors top-level subsystem names, command/tool inventories from the archived source
- Provides a **parity audit** mechanism to verify feature coverage against the original system
- Offers a CLI entrypoint for manifest output, subsystem listing, and parity summaries
- Designed to be orchestrated via AI coding agents (Claude Code, Codex, OmX, etc.)
---
## Installation & Setup
### Prerequisites
- Rust toolchain (stable, 1.75+): https://rustup.rs
- Cargo (bundled with Rust)
```bash
# Install Rust if needed
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
source $HOME/.cargo/env
# Clone the repository
git clone https://github.com/ultraworkers/claw-code-parity.git
cd claw-code-parity
# Build the project
cargo build
# Build in release mode for production use
cargo build --release
```
---
## Key CLI Commands
The project exposes a CLI binary. Run via `cargo run --` or the compiled binary:
```bash
# Print parity summary
cargo run -- summary
# Print the current workspace manifest
cargo run -- manifest
# List subsystems (with optional limit)
cargo run -- subsystems --limit 16
# Run parity audit against local ignored archive (when present)
cargo run -- parity-audit
# Inspect mirrored command inventories
cargo run -- commands --limit 10
# Inspect mirrored tool inventories
cargo run -- tools --limit 10
```
After `cargo build --release`, use the binary directly:
```bash
./target/release/claw-code-parity summary
./target/release/claw-code-parity manifest
./target/release/claw-code-parity subsystems --limit 8
./target/release/claw-code-parity parity-audit
```
---
## Project Structure
```
.
├── src/
│ ├── main.rs # CLI entrypoint and command dispatch
│ ├── commands.rs # Command port metadata and registry
│ ├── tools.rs # Tool port metadata and registry
│ ├── models.rs # Core data structures (subsystems, modules, backlog)
│ ├── port_manifest.rs # Workspace structure summary
│ └── query_engine.rs # Renders parity summary from active workspace
├── tests/ # Integration and unit tests
├── Cargo.toml
└── README.md
```
---
## Core Data Models (Rust)
### Subsystem and Module Definitions
```rust
// src/models.rs
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct Subsystem {
pub name: String,
pub description: String,
pub modules: Vec<Module>,
pub status: PortStatus,
}
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct Module {
pub name: String,
pub source_path: String,
pub ported: bool,
pub backlog_items: Vec<BacklogItem>,
}
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct BacklogItem {
pub id: String,
pub description: String,
pub priority: Priority,
}
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub enum PortStatus {
NotStarted,
InProgress,
Complete,
Blocked(String),
}
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub enum Priority {
High,
Medium,
Low,
}
```
### Command and Tool Metadata
```rust
// src/commands.rs
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct CommandEntry {
pub name: String,
pub description: String,
pub args: Vec<ArgSpec>,
pub ported: bool,
}
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct ArgSpec {
pub name: String,
pub required: bool,
pub arg_type: String,
}
pub fn command_registry() -> Vec<CommandEntry> {
vec![
CommandEntry {
name: "summary".to_string(),
description: "Render parity summary from active workspace".to_string(),
args: vec![],
ported: true,
},
CommandEntry {
name: "manifest".to_string(),
description: "Print current workspace manifest".to_string(),
args: vec![],
ported: true,
},
CommandEntry {
name: "subsystems".to_string(),
description: "List subsystems with optional limit".to_string(),
args: vec![ArgSpec {
name: "limit".to_string(),
required: false,
arg_type: "usize".to_string(),
}],
ported: true,
},
CommandEntry {
name: "parity-audit".to_string(),
description: "Run parity audit against local ignored archive".to_string(),
args: vec![],
ported: true,
},
]
}
```
---
## CLI Entrypoint Pattern
```rust
// src/main.rs
use clap::{Parser, Subcommand};
#[derive(Parser, Debug)]
#[command(name = "claw-code-parity", version, about = "Claw Code Rust Port Parity Tool")]
struct Cli {
#[command(subcommand)]
command: Commands,
}
#[derive(Subcommand, Debug)]
enum Commands {
/// Render the parity summary
Summary,
/// Print the workspace manifest
Manifest,
/// List subsystems
Subsystems {
#[arg(long, default_value = "16")]
limit: usize,
},
/// Run parity audit
ParityAudit,
/// List ported commands
Commands {
#[arg(long, default_value = "10")]
limit: usize,
},
/// List ported tools
Tools {
#[arg(long, default_value = "10")]
limit: usize,
},
}
fn main() {
let cli = Cli::parse();
match cli.command {
Commands::Summary => query_engine::render_summary(),
Commands::Manifest => port_manifest::print_manifest(),
Commands::Subsystems { limit } => {
let subsystems = models::all_subsystems();
for s in subsystems.iter().take(limit) {
println!("{}: {} [{:?}]", s.name, s.description, s.status);
}
}
Commands::ParityAudit => parity_audit::run(),
Commands::Commands { limit } => {
for cmd in commands::command_registry().iter().take(limit) {
println!(
"{} — {} [ported: {}]",
cmd.name, cmd.description, cmd.ported
);
}
}
Commands::Tools { limit } => {
for tool in tools::tool_registry().iter().take(limit) {
println!(
"{} — {} [ported: {}]",
tool.name, tool.description, tool.ported
);
}
}
}
}
```
---
## Query Engine: Rendering a Parity Summary
```rust
// src/query_engine.rs
use crate::models::{all_subsystems, PortStatus};
pub fn render_summary() {
let subsystems = all_subsystems();
let total = subsystems.len();
let complete = subsystems
.iter()
.filter(|s| matches!(s.status, PortStatus::Complete))
.count();
let in_progress = subsystems
.iter()
.filter(|s| matches!(s.status, PortStatus::InProgress))
.count();
printRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.