# Speq Code Guardrails

> TDD and code quality guardrails triggered by speq-implement.

- **Type:** Skill
- **Install:** `agentstack add skill-marconae-speq-skill-speq-code-guardrails`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [marconae](https://agentstack.voostack.com/s/marconae)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [marconae](https://github.com/marconae)
- **Source:** https://github.com/marconae/speq-skill/tree/main/.claude/skills/speq-code-guardrails

## Install

```sh
agentstack add skill-marconae-speq-skill-speq-code-guardrails
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Code Guardrails

**Clean Code** (Martin) TDD workflow and quality guardrails.

## Golden Rule

**No production code without a failing test first.**

## Evidence Rule

**No claim without evidence.** Run command, show output, then claim.

## TDD Cycle (London School)

```
RED    → Write failing test, run it, show failure
GREEN  → Minimal code to pass, run test, show pass
REFACTOR → Clean up, run test + lint, show output
```

Run ONLY the test you created/changed — not the full suite.

## Guiding Principles

| Principle | Meaning |
|-----------|---------|
| **KISS** | Simplest solution that works |
| **YAGNI** | Build for now, not hypotheticals |
| **DRY** | Extract duplication, don't copy-paste |
| **Single Responsibility** (**SOLID**) | One function = one purpose |
| **Boy Scout** | Leave code cleaner than you found it |
| **Root Cause** | **Five Whys** — fix the source, not the symptom |

## Design

- Config at high levels, behavior at low levels
- Polymorphism over conditionals
- Dependency injection for testability
- Law of Demeter: talk only to immediate collaborators

## Functions

- Small and focused
- Few arguments (≤3 ideal)
- No side effects
- No boolean flags — split into separate methods

## Naming

- Descriptive, unambiguous, pronounceable
- Named constants over magic numbers
- No prefixes or type encodings

## Comments

- Public/interface methods: brief doc comment (purpose only)
- Private methods: no comments
- No inline comments — code should be self-explanatory
- No work tracking (TODOs, FIXMEs, ticket refs)

## Code Smells

| Smell | Signal |
|-------|--------|
| Rigidity | Small changes cascade everywhere |
| Fragility | One change breaks unrelated code |
| Immobility | Can't reuse code elsewhere |
| Opacity | Hard to understand at a glance |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [marconae](https://github.com/marconae)
- **Source:** [marconae/speq-skill](https://github.com/marconae/speq-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-marconae-speq-skill-speq-code-guardrails
- Seller: https://agentstack.voostack.com/s/marconae
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.