clean-delivery

clean-delivery is a skill for Claude Code, Codex from giang6283623/minimal-vibe-coding-kit. It costs 57 tokens per session (933 once invoked), scanned A, original, MIT.

A step-by-step workflow for delivering one small, observable code change. It uses checks for planning, implementation, design boundaries, security, and verification, with test-driven development (TDD) where appropriate.

In plain words
What is it for?
Use it to plan and implement a focused feature or fix, define what is in scope, choose suitable tests, and verify the result with reproducible commands.
Why use it?
It prevents broad, unclear changes and makes the evidence for a completed change explicit. It also identifies missing verification instead of treating it as proof.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Good fit Use it to plan and implement a focused feature or fix, define what is in scope, choose suitable tests, and verify the result with reproducible commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giang6283623/minimal-vibe-coding-kit/clean-delivery
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.

Any agent
npx skills add giang6283623/minimal-vibe-coding-kit --skill clean-delivery
Clone the repo
git clone --depth 1 https://github.com/giang6283623/minimal-vibe-coding-kit

Made for: Claude Code, Codex.

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 clean-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/clean-delivery.svg)](https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/clean-delivery)
Your own site
<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/clean-delivery"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/clean-delivery.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 933 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 $0.00057 $0.00933
Opus 5 $0.00028 $0.00466
Sonnet 5 $0.00011 $0.00187
Haiku 4.5 $0.00006 $0.00093

Measured 8d ago against content hash 8f1b2c5aacaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

clean-delivery 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate-story.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/clean-delivery/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.

Clean Delivery

Deliver one small, observable behavior slice with evidence. The six stages are quality gates, not six mandatory agents.

Before work

Read these files completely:

  1. references/story-template.md
  2. references/verification-tiers.md
  3. references/architecture-contract.md
  4. references/proof-return-mapping.md

Read backbone.yml and repository instructions. Refuse protected-path changes without approval. Never install tools, enable hooks, or broaden authority merely to satisfy a gate.

Required input contract

Freeze one story before implementation. Record:

  • one observable behavior;
  • in-scope and out-of-scope work;
  • editable paths and protected verifier assets;
  • acceptance criteria;
  • the expected failing check and proof commands;
  • a low, medium, high, or critical risk tier.

Create the story from references/story-template.md, then validate it:

node .vibekit/skills/clean-delivery/scripts/validate-story.mjs <story.md>

A missing verifier is a declared proof gap, not permission to invent evidence. "not-configured: " is valid only when the gate is not proportionate to the slice.

Six gates

1. Specify

Turn the request into one story whose outcome can be observed from outside the implementation. Resolve material ambiguity before code. Keep Gherkin optional: clear bullet criteria are acceptable.

Exit when the story validator passes and scope is frozen.

2. Code

Run the smallest relevant check before implementation and capture the expected failure. Implement only enough production code to make the behavior pass. Do not weaken tests or protected verifier assets.

For a documentation-only or configuration-only slice, record why a red unit test is not applicable and use the smallest deterministic validator that can fail before the change.

Exit when the red evidence is authentic and the minimal behavior passes.

3. Clean

Improve names, duplication, function size, and error clarity without changing behavior. Prefer domain language and single-purpose units. Rerun the same focused proof after each meaningful cleanup.

Read the full file on GitHub · 99 lines

Files

What ships with it

6 files 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. 8d ago First seen · 99 lines · 57 tokens per session scan A 8f1b2c5aacaa

Subscribe to this mod's changes

clean-delivery is a skill published in the GitHub repository giang6283623/minimal-vibe-coding-kit (21 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 933 once invoked, about $0.0003 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 2026-08-30.