Manor Coding Guardrails

SkillDev tools

Use when writing, reviewing, or refactoring Manor code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Manor Coding Guardrails skill

What this skill tells your AI

The instructions your AI receives, as published by manor-os/manor-ai in .agents/skills/manor-coding-guardrails/SKILL.md and read by ahel’s review.

Adapted from Karpathy Guidelines (MIT). Preserve these core directives when working in Manor.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • Do not select a "safe", "simple", or reversible default when interpretations change persisted state, user-visible behavior, lifecycle, or external effects. Stop and request a decision.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports, variables, and functions that your changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" -> "Write tests for invalid inputs, then make them pass."
  • "Fix the bug" -> "Write a test that reproduces it, then make it pass."
  • "Refactor X" -> "Ensure tests pass before and after."

For multi-step tasks, state a brief plan:

1. [Step] -> verify: [check]
2. [Step] -> verify: [check]
3. [Step] -> verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

Manor Boundary Rule

These rules do not permit a Manor shortcut around a shared contract. When a change crosses Workspace, Task, Plan, Workflow, approval, credits, Knowledge, artifact, lifecycle, or Blueprint boundaries, REQUIRED SUB-SKILL: use $manor-workspace-architecture before editing. Keep all entry surfaces on the same authorization, approval, credit, lifecycle, and durable-artifact path.

Use another specialized Manor skill only when its trigger directly matches the request. It adds domain-specific context; it never replaces the four core guardrails above.

Signals

GitHub stars
171
Forks
52
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
manor-coding-guardrails
Source
github.com/manor-os/manor-ai