owner-driven-development

owner-driven-development is a skill for Claude Code, Codex from wazimmerman/zimster. It costs 27 tokens per session (2,130 once invoked), scanned A, original, MIT.

A development workflow in which one persistent owner guides an approved plan, makes the implementation changes, records the Git outcome, and reviews the result.

In plain words
What is it for?
Executing planned feature work through small vertical slices, test-first changes, focused review, correction, and final completion checks.
Why use it?
It keeps responsibility and decision-making clear while requiring tests, risk-based reviews, and fresh evidence before completion is claimed.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the zimster plugin — 12 skills, 1 command, 4 agents, 1 hook shipped together

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/wazimmerman/zimster/owner-driven-development
Any agent
npx skills add wazimmerman/zimster --skill owner-driven-development
Clone the repo
git clone --depth 1 https://github.com/wazimmerman/zimster

Made for: Claude Code, Codex.

Or install zimster, the plugin that ships this one along with the rest of its 12 skills, 1 command, 4 agents, 1 hook.

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 owner-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/wazimmerman/zimster/owner-driven-development.svg)](https://agentmods.dev/skills/wazimmerman/zimster/owner-driven-development)
Your own site
<a href="https://agentmods.dev/skills/wazimmerman/zimster/owner-driven-development"><img src="https://agentmods.dev/badge/skills/wazimmerman/zimster/owner-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,130 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00027 $0.02130
Opus 5 $0.00014 $0.01065
Sonnet 5 $0.00005 $0.00426
Haiku 4.5 $0.00003 $0.00213

Measured 6d ago against content hash 3213c018af61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

owner-driven-development 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 6d 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.

plugins/zimster/skills/owner-driven-development/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Owner-Driven Development

The root agent is the persistent implementation owner. It understands the mission, implements related vertical slices, preserves architectural invariants, and resolves findings. It is not a passive dispatcher.

Core loop

profile and Git disposition
→ baseline
→ highest-value vertical slice
→ RED → minimal GREEN → REFACTOR
→ affected evidence
→ risk-triggered seam review
→ next slice
→ final integration review when required
→ one consolidated correction wave
→ fresh completion evidence
→ deterministic candidate-completion gate
→ finishing-a-development-branch

1. Establish control

Before production edits:

  • select Micro, Standard, or High risk and record the rationale;
  • read the mission/plan and resolve contradictions;
  • inspect repository root, branch, worktrees, status, and project instructions;
  • discover repository-declared verification commands;
  • record unavailable hardware, service, credential, or human evidence;
  • initialize durable state when any deterministic trigger below applies.

If requirements conflict or cannot all be satisfied, stop as BLOCKED_BY_REQUIREMENT; do not disguise it as an environment problem.

Semantic review and candidate state

The owner's inline inspection is self_review, including an owner-inline change review. It never becomes independent_review by being thorough. Keep checkout integrity, evidence validity, self-review, and semantic approval separate. REVIEW_CHECKOUT_UNCHANGED and REVIEW_CHECKOUT_CHANGED say only whether the bounded review checkout changed; checkout integrity does not imply semantic approval.

Eligible Micro work may reach owner-only completion only after deterministic eligibility and complete matrix proof. Standard and High-risk work require an approved clean-context independent_review for the exact candidate head. High-risk work additionally requires its load-bearing obligations and final independent integration review. When review is unavailable, record OWNER_VERIFIED_REVIEW_UNAVAILABLE, not readiness. Only a valid matrix plus profile-appropriate approval may produce CANDIDATE_COMPLETE.

Read the full file on GitHub · 228 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 228 lines · 27 tokens per session scan A 3213c018af61

Subscribe to this mod's changes

owner-driven-development is a skill published in the GitHub repository wazimmerman/zimster (2 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 2,130 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

build-test

Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.

nexu-io/open-design · 31 tokens

test-driven-development

Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.

KbWen/agentic-os · 23 tokens

rudder

Use locally captured coding-session intent to resolve a device-local behavioral spec, generate focused tests from that spec, implement the smallest production changes through red-green TDD, and verify coverage with the repository's native tooling. Use when the user asks to run Rudder, create or regenerate tests for…

RudderCode/Rudder · 101 tokens

TDD 开发纪律助手

引导开发过程遵循测试先行、红绿重构和回归验证纪律。.

cdavid817/vanehub-ai · 27 tokens

treework-manual

Use TreeWork Manual when the user asks for it, or when the Agent judges that organizing ongoing, multi-part work as a persistent Markdown Tree would improve direction, continuity, recovery, or handoff. Adapt the Tree's depth and document detail to the user's needs, domain, and situation rather than a fixed threshold.

Johnny-xuan/TreeWork · 68 tokens

treework

Use TreeWork, a tree-guided development plugin for complex or evolving software projects that need staged alignment, pre-coding technical Specs, declarative project-tree planning, branch-scoped Git worktrees, durable recovery, and protected completion. It teaches the Agent to move through development along the Tree…

Johnny-xuan/TreeWork · 68 tokens