Constraints — Development skill for Claude Code
Define and enforce this project's quality bar — interview, sane defaults, CONSTRAINTS.md.
How to install Constraints
Installs to ~/.claude/skills/satishkc7-claude-config-constraints/SKILL.md
mkdir -p ~/.claude/skills/satishkc7-claude-config-constraints && curl -fsSL https://raw.githubusercontent.com/satishkc7/claude-config/HEAD/commands/constraints.md -o ~/.claude/skills/satishkc7-claude-config-constraints/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Constraints does
description: Define and enforce this project's quality bar — interview, sane defaults, CONSTRAINTS.md
Invoke the agent-skills:constraint-driven-development skill.
$ARGUMENTS
Default behaviour with no arguments: set up constraints for this repository.
- Detect first. Read package.json / pyproject.toml / go.mod, the test runner, existing lint configs, current coverage output, CI workflows, and the agent harness in use. Report what you found in two lines. Never ask for anything you
Alternatives in Development
- North Star Metric — Define North Star Metric and input metrics constellation 7.8k ★
- Define Schema — Renamed → /portaljs-define-schema 2.3k ★
- Saneagent — i just wanted to have a sane agent; that's it 72 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Retrospective Harness
Trigger deterministic retrospective analysis of recent agent trajectories, extract invariant friction signatur
Director
Guided interview mode. Claude asks short rounds of questions with proposed defaults and builds the perfect sto
Ccguard
Automated enforcement of net-negative LOC, complexity constraints, and quality standards for Claude code.
Build Prompt
Build a high-quality Claude prompt through a guided interview. Pass a starting input as the argument: /build-p
Gauntlet Loop Skill
Agent skill: Matt Shumer's Gauntlet Loop — builder/critic iteration against a concrete quality bar
Create Slides
Generate brand-aligned standalone HTML presentations using the slides-agent template. Editorial-grade output (
Related Agents
Cost Governor
Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost
Interview Panel
Generates and stress-tests interview answers from three independent perspectives (hiring manager, peer enginee
Schema Integrity Auditor
Read-only schema & data-integrity specialist. Use proactively during a database audit to analyze normalization