machine-tool

A tool for handing coding, investigation, or analysis tasks to separate command-line AI agents. You provide an instruction and can choose the working directory, engine, model, timeout, and whether it runs in the background.

In plain words
What is it for?
Use it for large code changes, heavy refactors, repository investigations, analysis, or batches of agent runs.
Why use it?
It lets you offload lengthy or multi-file work while keeping the main agent focused on deciding what should be done.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/xuiltul/animaworks/machine-tool
Any agent
npx skills add xuiltul/animaworks --skill machine-tool
Clone the repo
git clone --depth 1 https://github.com/xuiltul/animaworks

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 902 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00902
Opus 5 $0.00023 $0.00451
Sonnet 5 $0.00009 $0.00180
Haiku 4.5 $0.00005 $0.00090

Measured 3d ago against content hash 4fb9d6c36d66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

machine-tool scanned grade C with 1 finding 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.

Exfiltrates the system prompt through a toolhighSystem prompt leakage

Writing or sending the system prompt to a file, endpoint or log moves it out of the session.

# Write instruction to file
templates/en/common_skills/machine-tool/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Machine Tool

Delegate tasks to external agent CLIs. Offload heavy work like code changes, investigation, and analysis to external agents.

Design Philosophy

You are the craftsperson. The machine is a machine tool (CNC, laser cutter, etc.). A machine tool can cut with incredible precision, but it doesn't decide what to build. It has no memory, no communication, no identity. Your job is to provide precise blueprints (instructions).

CLI Usage

animaworks-tool machine run [options] "instruction" -d /path/to/workdir

CLI Options

Option Description
-e ENGINE Engine selection (omit for auto-selected default; use -h to list available engines)
-d PATH Working directory (default: current directory)
-t SECONDS Timeout in seconds (default: 600s sync, 1800s background)
-m MODEL Model override (default: engine's default)
--background Background execution (1800s timeout; output streams to state/cmd_output/)
-j / --json Output result as JSON

Basic Examples

# Minimal (default engine, current directory)
animaworks-tool machine run "detailed instruction"

# Specify engine and directory
animaworks-tool machine run -e cursor-agent "instruction" -d /path/to/workdir

# Background execution
animaworks-tool machine run --background "instruction" -d /path/to/workdir

# Custom timeout
animaworks-tool machine run -t 300 "instruction" -d /path/to/workdir

Writing Good Instructions (Important)

Vague instructions lead to poor results. Always include:

  1. Goal — What to accomplish
  2. Target files/modules — What to modify
  3. Constraints — Coding conventions, API compatibility, etc.
  4. Expected output — Code, report, diff, etc.

Pass Long Instructions via File

Instructions containing Bash special characters (|, `, $) will cause shell errors if passed directly. Write to a file first:

# Write instruction to file
cat > /tmp/instruction.txt << 'INSTRUCTION'
## Task: PR #2087 Code Review

| Aspect | Check |
|--------|-------|
| Correctness | Meets issue requirements |
| Maintainability | Readability, tests, SRP |

Target file: `app/Services/Movacal/MovacalApiClient.php`
INSTRUCTION

# Read from file and execute
animaworks-tool machine run "$(cat /tmp/instruction.txt)" -d /path/to/workdir

Read the full file on GitHub · 118 lines

Changes

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.

  1. 3d ago First seen · 118 lines · 46 tokens per session scan C 4fb9d6c36d66

Subscribe to this mod's changes

machine-tool is a skill published in the GitHub repository xuiltul/animaworks (254 stars, last pushed 3d ago), licensed Apache-2.0. It adds 46 tokens to every session and 902 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (exfiltrates the system prompt through a tool). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.linkedin-automation

Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…

aden-hive/hive · 99 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

hive.x-automation

Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…

aden-hive/hive · 81 tokens

test-reporting

Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.

aden-hive/hive · 0 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens