ownership-partitioning

ownership-partitioning is a skill for Claude Code from dyCuong03/unity-agent-team. It costs 47 tokens per session (909 once invoked), scanned A, original, MIT.

A rule system for dividing repository files among parallel coding agents using path patterns. It records which agent may write each area and which files are read-only or forbidden.

In plain words
What is it for?
Use it to define ownership for source, tooling, configuration, shared, and restricted paths, then check ownership before moving to the next pipeline phase.
Why use it?
It prevents two agents from editing the same files and catches writes outside an agent's assigned area.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python .claude/scripts/orchestrate.py ownership-check <your-agent-name> \.

Good fit Use it to define ownership for source, tooling, configuration, shared, and restricted paths, then check ownership before moving to the next pipeline phase.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/dyCuong03/unity-agent-team
agentmods
npx agentmods add skills/dycuong03/unity-agent-team/ownership-partitioning

Made for: Claude Code.

Wrote 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.

agentmods badge for ownership-partitioning

README.md
[![agentmods](https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/ownership-partitioning/github.svg)](https://agentmods.dev/skills/dycuong03/unity-agent-team/ownership-partitioning)
Your own site
<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/ownership-partitioning"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/ownership-partitioning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ownership-partitioning

Your own site · 80×15
<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/ownership-partitioning"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/ownership-partitioning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 909 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00047 $0.00909
Opus 5.5 $0.00019 $0.00364
Sonnet 5.5 $0.00009 $0.00182
Haiku 4.5 $0.00005 $0.00091

Measured 11d ago against content hash a48ec7a8eeba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ownership-partitioning 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 11d 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.

.claude/skills/ownership-partitioning/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ownership Partitioning

This skill is loaded into every writer agent (unity-dev, data-tool) whenever pipeline.json.parallel_allowed == true. It is enforced at runtime by orchestrate.py ownership-check.

Source of Truth

workspace/ownership.lock.json. Format:

{
  "partitions": {
    "unity-dev": ["Assets/Scripts/Combat/**", "Assets/Scripts/Movement/**"],
    "data-tool": ["Assets/Editor/Combat/**", "Assets/Configs/Combat/**"]
  },
  "shared_read_only": ["ProjectSettings/**", "Packages/**"],
  "forbidden": ["Assets/Plugins/**"],
  "rationale": "Combat refactor — runtime vs tooling are disjoint"
}

Globs are repo-root-relative, POSIX-style (use /, not \). ** matches any number of path segments.

Rules

  1. You may only write to files matching one of YOUR partition globs. Writing to another agent's partition is a hard violation.

  2. shared_read_only files may be read by anyone but NEVER written this session. If you genuinely need to change one, escalate.

  3. forbidden files must not be touched at all (typically generated code, third-party plugins, lockfiles).

  4. Before signaling the next phase, run the check explicitly:

    python .claude/scripts/orchestrate.py ownership-check <your-agent-name> \
        Assets/Scripts/Combat/Health.cs Assets/Scripts/Combat/Damage.cs
    

    Non-zero exit means you have a violation. Roll back that file and re-run.

Architect Responsibilities

For large / critical complexity, the architect writes workspace/ownership.lock.json as part of the approved_plan.json phase. The partition must:

  • Have non-overlapping globs across agents
  • Cover every file the plan expects to change
  • Not include shared_read_only paths inside any partition

The orchestrate.py gate refuses to enter the implementation phase if ownership.lock.json is missing for any plan with parallel_allowed=true.

Triage Responsibilities

For tiny / small / medium complexity with a single writer, triage may either (a) omit ownership.lock.json entirely (unrestricted single writer), or (b) write a single-agent partition to lock the writer to a known glob.

Read the full file on GitHub · 99 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. 11d ago First seen · 99 lines · 47 tokens per session scan A a48ec7a8eeba

Subscribe to this mod's changes

ownership-partitioning is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 909 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.

Related

Other skills, from other repositories