
Claw Code Harness
Inspect, audit, and inventory a Claude Code–style agent harness after porting or customizing it in Python or Rust.
Overview
Claw Code Harness is an agent skill for the Build phase that inspects and audits a Python (and in-progress Rust) rewrite of the Claude Code harness via manifest, parity, and inventory CLI tooling.
Install
npx skills add https://github.com/aradotso/trending-skills --skill claw-code-harnessWhat is this skill?
- CLI and Python modules to summarize the port manifest and list subsystems
- Parity auditing against an archived Claude Code harness source
- Tool and command inventory queries from importable harness code
- Clean-room Python rewrite with an in-progress Rust port path
- Unittest discovery workflow for verifying the workspace from source
- Python core with optional requirements.txt; Rust port in progress
- Modules include commands.py, main.py, and models for port metadata
Adoption & trust: 670 installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You ported or maintain a custom agent harness but cannot quickly see which subsystems, tools, and commands match the original or what the manifest actually contains.
Who is it for?
Indie builders maintaining a clean-room Claude Code harness fork who need manifest and parity tooling without spelunking the whole codebase.
Skip if: Teams who only use stock Claude Code with no custom harness, or anyone looking for slide decks or sales demo scripts.
When should I use this skill?
User asks to set up claw-code harness, inspect tools, run parity audit, manifest summary, command inventory, subsystems list, or tool port metadata.
What do I get? / Deliverables
You get manifest summaries, subsystem lists, parity audit results, and searchable tool/command inventories from a single CLI so harness changes stay documented and verifiable.
- Manifest summary and subsystem enumeration from CLI
- Parity audit report against archived harness behavior
- Tool and command inventory listings
Recommended Skills
Journey fit
Harness manifests, parity checks, and tool inventories belong on the build shelf where you wire up and maintain agent runtimes—not in launch or grow. Subphase agent-tooling is the canonical home for harness CLIs, command metadata, and subsystem enumeration tied to coding agents.
How it compares
Use for harness introspection and parity auditing, not as a drop-in replacement for the official Claude Code product install.
Common Questions / FAQ
Who is claw-code-harness for?
Solo and indie developers who run or port an open harness around Claude Code–style agents and need CLI-level manifest, inventory, and parity checks from source.
When should I use claw-code-harness?
During Build (agent-tooling) when you set up the repo, run a parity audit, print manifest summaries, or enumerate tools and commands before wiring new agent workflows.
Is claw-code-harness safe to install?
It is used from a cloned Git repository with local Python tests; review the Security Audits panel on this Prism page and pin the commit you trust before running audits on production-adjacent trees.
SKILL.md
READMESKILL.md - Claw Code Harness
# Claw Code Harness > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. Claw Code is a clean-room Python (with Rust port in progress) rewrite of the Claude Code agent harness. It provides tooling to inspect the port manifest, enumerate subsystems, audit parity against an archived source, and query tool/command inventories — all via a CLI entrypoint and importable Python modules. --- ## Installation ```bash # Clone the repository git clone https://github.com/instructkr/claw-code.git cd claw-code # Install dependencies (standard library only for core; extras for dev) pip install -r requirements.txt # if present, else no external deps required # Verify the workspace python3 -m unittest discover -s tests -v ``` No PyPI package yet — use directly from source. --- ## Repository Layout ``` . ├── src/ │ ├── __init__.py │ ├── commands.py # Python-side command port metadata │ ├── main.py # CLI entrypoint │ ├── models.py # Dataclasses: Subsystem, Module, BacklogState │ ├── port_manifest.py # Current Python workspace structure summary │ ├── query_engine.py # Renders porting summary from active workspace │ ├── task.py # Task primitives │ └── tools.py # Python-side tool port metadata └── tests/ # Unittest suite ``` --- ## CLI Reference All commands are invoked via `python3 -m src.main <command>`. ### `summary` Render the full Python porting summary. ```bash python3 -m src.main summary ``` ### `manifest` Print the current Python workspace manifest (file surface + subsystem names). ```bash python3 -m src.main manifest ``` ### `subsystems` List known subsystems, with optional limit. ```bash python3 -m src.main subsystems python3 -m src.main subsystems --limit 16 ``` ### `commands` Inspect mirrored command inventory. ```bash python3 -m src.main commands python3 -m src.main commands --limit 10 ``` ### `tools` Inspect mirrored tool inventory. ```bash python3 -m src.main tools python3 -m src.main tools --limit 10 ``` ### `parity-audit` Run parity audit against a locally present (gitignored) archived snapshot. ```bash python3 -m src.main parity-audit ``` > Requires the local archive to be present at its expected path (not tracked in git). --- ## Core Modules & API ### `src/models.py` — Dataclasses ```python from src.models import Subsystem, Module, BacklogState # A subsystem groups related modules sub = Subsystem(name="tool-harness", modules=[], status="in-progress") # A module represents a single ported file mod = Module(name="tools.py", ported=True, notes="tool metadata only") # BacklogState tracks overall port progress state = BacklogState( total_subsystems=8, ported=5, backlog=3, notes="runtime slices pending" ) ``` ### `src/tools.py` — Tool Port Metadata ```python from src.tools import get_tools, ToolMeta tools: list[ToolMeta] = get_tools() for t in tools[:5]: print(t.name, t.ported, t.description) ``` ### `src/commands.py` — Command Port Metadata ```python from src.commands import get_commands, CommandMeta commands: list[CommandMeta] = get_commands() for c in commands[:5]: print(c.name, c.ported) ``` ### `src/query_engine.py` — Porting Summary Renderer ```python from src.query_engine import render_summary summary_text: str = render_summary() print(summary_text) ``` ### `src/port_manifest.py` — Manifest Access ```python from src.port_manifest import get_manifest, ManifestEntry