constraint-driven-development

constraint-driven-development is a skill for Claude Code from GuillemRoca/agent-skills-android. It costs 172 tokens per session (5,058 once invoked), scanned A, original, MIT.

A process for writing a project's quality bar as rules with chosen numbers and commands that check them. It is intended for Android projects and turns expectations into checks that persist beyond a conversation.

In plain words
What is it for?
Use it to define and enforce thresholds for coverage, static analysis, security, performance, accessibility, and module boundaries.
Why use it?
It makes standards explicit before work begins and reduces the chance that an agent skips tests or weakens checks just to get a passing build.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the agent-skills-android plugin — 30 skills, 8 commands, 3 agents shipped together

Good fit Use it to define and enforce thresholds for coverage, static analysis, security, performance, accessibility, and module boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guillemroca/agent-skills-android/constraint-driven-development
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.

Any agent
npx skills add GuillemRoca/agent-skills-android --skill constraint-driven-development
Clone the repo
git clone --depth 1 https://github.com/GuillemRoca/agent-skills-android

Made for: Claude Code.

Or install agent-skills-android, the plugin that ships this one along with the rest of its 30 skills, 8 commands, 3 agents.

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 constraint-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/constraint-driven-development/github.svg)](https://agentmods.dev/skills/guillemroca/agent-skills-android/constraint-driven-development)
Your own site
<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/constraint-driven-development"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/constraint-driven-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for constraint-driven-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/constraint-driven-development"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/constraint-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00172 $0.05058
Opus 5.5 $0.00069 $0.02023
Sonnet 5.5 $0.00034 $0.01012
Haiku 4.5 $0.00017 $0.00506

Measured 12d ago against content hash 93b5fab41ac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

constraint-driven-development 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 12d 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/constraint-driven-development/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Constraint-Driven Development

Overview

Other skills describe what good looks like: code-review-and-quality gives five axes, test-driven-development a cycle, security-and-hardening a threat list. That is prose an agent may or may not follow, and none of it survives the session. This skill produces a written record of this project's bar, with numbers and the command that checks each one, that outlives the conversation and runs mechanically.

The reason: when you wrote the code, reading it told you whether it was good. An agent writes more in an afternoon than you will read that week, so judgement moves out of your head and into checks that run around the loop. Those checks need to exist, carry numbers you chose, and fire close enough to the work that the agent fixes its own output.

Spec-driven development says what to build. Test-driven development proves it works. Constraint-driven development defines "good enough to ship" before anyone argues about it in a pull request.

When to Use

  • Starting a project or significant feature and no quality bar is written down
  • The user asks to "set up constraints", "add quality gates", "define our standards"
  • An agent is producing volume nobody reads line by line
  • CI runs lint, detekt, and tests, but nobody can say which ones block a merge
  • Coverage, startup time, APK size, or accessibility get argued per PR instead of decided once
  • Before /build auto or any autonomous loop, where the only thing between the agent and main is a test suite the agent also wrote

Skip when:

  • CONSTRAINTS.md already exists and the user isn't changing it — read and follow it
  • Spikes, throwaway prototypes, one-off scripts
  • The user wants a review now (code-review-and-quality) or a pipeline built (ci-cd-and-automation)

Non-interactive contexts (CI, scheduled loops, autonomous runs): the interview needs a live user. If constraints are missing, apply the Floor below, say you did, and flag the rest for a human.

Read the full file on GitHub · 336 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. 12d ago First seen · 336 lines · 172 tokens per session scan A 93b5fab41ac3

Subscribe to this mod's changes

constraint-driven-development is a skill published in the GitHub repository GuillemRoca/agent-skills-android (2 stars, last pushed 13d ago), licensed MIT. It adds 172 tokens to every session and 5,058 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-04.

Related

Other skills, from other repositories

spec-kitty-implement-review

Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…

Priivacy-ai/spec-kitty · 120 tokens

spec-kitty-mission-system

Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…

Priivacy-ai/spec-kitty · 160 tokens

spec-kitty-program-orchestrate

Orchestrate a multi-repo, multi-mission Spec Kitty program end-to-end: run specify → plan → tasks → implement → review → merge → mission-review → post-merge fixes across several repositories in a defined dependency order, using background sub-agents for parallel work and a pulse-heartbeat safety net for long…

Priivacy-ai/spec-kitty · 188 tokens

spec-kitty-runtime-review

Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…

Priivacy-ai/spec-kitty · 85 tokens

spk-run-verdict-capture

Set a Spec Kitty work-package review verdict through the deterministic event-log seam, so every agent harness records approve/reject the same way.

Priivacy-ai/spec-kitty · 35 tokens

spk-run-implement-review

Orchestrate Spec Kitty work-package implementation and review loops until all packages are done, approved, or correctly rejected.

Priivacy-ai/spec-kitty · 30 tokens