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.
npx agentmods add skills/unrealandychan/clean-code-skill/extreme-constraintsnpx skills add unrealandychan/clean-code-skill --skill extreme-constraintsgit clone --depth 1 https://github.com/unrealandychan/clean-code-skillWrote 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.
[](https://agentmods.dev/skills/unrealandychan/clean-code-skill/extreme-constraints)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
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.
- 6d ago First seen · 69 lines · 57 tokens per session scan A 238505879886
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.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nunit-testing
Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.
nw-diverge
Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence. Use when the team has a validated problem but hasn't chosen a solution approach.