extreme-constraints-and-vibe-coding

extreme-constraints-and-vibe-coding is a skill for Claude Code, Codex from unrealandychan/clean-code-skill. It costs 57 tokens per session (891 once invoked), scanned A, original, MIT.

A framework for AI-assisted coding that sets requirements and automated checks before code is generated, including executable Given-When-Then specifications, mutation testing, test coverage, and code-quality measurements.

In plain words
What is it for?
Use it when starting AI coding work, writing behavior specifications, testing whether tests catch faults, and measuring code quality.
Why use it?
It shifts human attention from reading every generated line to defining constraints and checking whether the result meets them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/unrealandychan/clean-code-skill/extreme-constraints
Any agent
npx skills add unrealandychan/clean-code-skill --skill extreme-constraints
Clone the repo
git clone --depth 1 https://github.com/unrealandychan/clean-code-skill

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 extreme-constraints-and-vibe-coding

README.md
[![agentmods](https://agentmods.dev/badge/skills/unrealandychan/clean-code-skill/extreme-constraints.svg)](https://agentmods.dev/skills/unrealandychan/clean-code-skill/extreme-constraints)
Your own site
<a href="https://agentmods.dev/skills/unrealandychan/clean-code-skill/extreme-constraints"><img src="https://agentmods.dev/badge/skills/unrealandychan/clean-code-skill/extreme-constraints.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 891 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 $0.00057 $0.00891
Opus 5 $0.00028 $0.00445
Sonnet 5 $0.00011 $0.00178
Haiku 4.5 $0.00006 $0.00089

Measured 6d ago against content hash 238505879886, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

extreme-constraints-and-vibe-coding 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.

skills/extreme-constraints/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Uncle Bob's "Extreme Constraints" Vibe Coding Skill

Inspired by Robert C. Martin ("Uncle Bob"), author of Clean Code.

"My current strategy is to not read any of the code written by my agents. That's the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others." — Robert C. Martin (Uncle Bob)


Purpose

Empower developers and AI agents to practice high-velocity Vibe Coding with zero compromise on software craftsmanship. Instead of wasting cognitive bandwidth reading machine-generated token syntax, human developers operate "one floor up" as Constraint Architects, surrounding AI agents with an uncompromising automated verification gauntlet.


When to Invoke This Skill

Trigger this skill when:

  • Starting an agentic or vibe coding task (/extreme-constraints, /vibe-guard).
  • Writing executable Given-When-Then specifications prior to code generation (/gherkin-spec).
  • Running mutation testing to audit test suite fault detection (/mutation-audit).
  • Calculating Cyclomatic Complexity ($M \le 10$) and CRAP scores ($CRAP \le 30$) (/crap-metric).
  • Verifying whether AI-generated code survives the full automated gauntlet before merging (/gauntlet-check).
  • Refactoring legacy code with agent assistance while preserving zero-defect guarantees.

The 6 Constraint Pillars

 ┌──────────────────────────────────────────────────────────────┐
 │             THE 6 EXTREME CONSTRAINT PILLARS                 │
 └──────────────────────────────┬───────────────────────────────┘
                                │
   1. Executable Specifications ── Gherkin (Given-When-Then) acceptance criteria
   2. Deterministic Test Baselines ── 100% green test suite, >90% branch coverage
   3. Mutation Testing ──────────── Mutant slaughterhouse (Stryker/Mutmut/Pitest)
   4. Complexity & CRAP Gates ───── Cyclomatic Complexity ≤ 10, CRAP index ≤ 30
   5. Architectural Invariants ──── Domain isolation, immutable VOs, Aggregate boundaries
   6. Automated Static QA ───────── Zero-tolerance linter, type checker, security scan

Read the full file on GitHub · 69 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 · 69 lines · 57 tokens per session scan A 238505879886

Subscribe to this mod's changes

extreme-constraints-and-vibe-coding is a skill published in the GitHub repository unrealandychan/clean-code-skill (6 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 891 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 2026-08-31.