--- title: "Constraint-driven development: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/skills/addyosmani-constraint-driven-development/ description: "Records project quality constraints with measured baselines, enforcement commands and reviewable exceptions." --- # Constraint-driven development: review, setup & limitations · Undominated.ai > Records project quality constraints with measured baselines, enforcement commands and reviewable exceptions. [← Explore all skills](/skills/) DEVELOPMENT WORKFLOW / Addy Osmani # Constraint-driven development Records project quality constraints with measured baselines, enforcement commands and reviewable exceptions. [See setup guidance ↓](#setup)[Original source ↗](https://github.com/addyosmani/agent-skills/tree/1401c8b8030e023baeebb31781a6653fe8e93026/skills/constraint-driven-development) SOURCE REVIEW Reviewed 2026-10-07 Evidence 3 linked sources Publisher Addy Osmani Licence [MIT ↗](https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/LICENSE) Revision 1401c8b8030e [Read what was—and wasn’t—checked ↓](#review) “Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set up constraints" or "define our standards", when the user wants dimensions they care about — accessibility, web performance, coverage — set up as enforced constraints, when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.” [Addy Osmani · upstream description ↗](https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/skills/constraint-driven-development/SKILL.md) Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - Pairs each threshold with a concrete check and separates written policy from scripted enforcement. - Reviews weakened thresholds, removed assertions and new suppressions, using ratchets when a target number is not established. ### A good fit for - Stopping an agent from adding a skip or a suppression to pass - Recording numeric thresholds the repository actually uses ### Weigh up before choosing - Suggested coverage/performance values are defaults, not measured guarantees. Example scanner commands need exit-code/severity wiring; a green invocation alone is not necessarily a blocking security gate. - Reviewed definition and licence are pinned; installation and real-task outcomes for this resource were not tested. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - skills/constraint-driven-development/SKILL.md (complete frontmatter and body) - https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/LICENSE (applicable licence text) ### Our findings - Pairs each threshold with a concrete check and separates written policy from scripted enforcement. - Reviews weakened thresholds, removed assertions and new suppressions, using ratchets when a target number is not established. - Writes CONSTRAINTS.md and agent/CI configuration, installs selected tools and runs tests, scanners or browser measurements. ### Not established by this review - Host discovery, task execution and model quality were not tested. - Referenced helpers, sibling plugins and external service operations were not exhaustively audited or executed. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Add a skill to your workflow. [Upstream setup instructions ↗](https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/README.md) DOCUMENTED COMMAND npx skills@1.7.1 add https://github.com/addyosmani/agent-skills/tree/1401c8b8030e023baeebb31781a6653fe8e93026/skills/constraint-driven-development --skill constraint-driven-development Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Use the exact reviewed directory/revision and select the intended host/project scope in Skills CLI. - Retain all supporting files; separately configure companion skills, runtimes and service credentials named in the definition. - Review the resulting diff and use an isolated target before any migration, deployment, load test or warehouse operation. ### Before you start - An agreed project quality policy and the tooling for each selected dimension; existing baselines should be measured first. ### Compatibility Agent Skills-compatible hosts ### Host-mediated code, files and tools - Writes CONSTRAINTS.md and agent/CI configuration, installs selected tools and runs tests, scanners or browser measurements. - The host enforces permissions; installing instructions does not itself create a sandbox. ### Cost model Source is available under the stated licence. Model usage, compute and connected services can incur charges. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - [Skill definition ↗](https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/skills/constraint-driven-development/SKILL.md) Checked 2026-10-07 https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/skills/constraint-driven-development/SKILL.md Supports: summary, whySelected, limitations, access, review - [Repository licence ↗](https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/LICENSE) Checked 2026-10-07 https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/LICENSE Supports: Redistribution terms - [Install instructions ↗](https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/README.md) Checked 2026-10-07 https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/README.md Supports: Documented install path KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### API and Interface Design ↗ Designs stable API contracts, consistent errors and retry-safe idempotency behavior.](/skills/addyosmani-api-and-interface-design/)[### Dispatching Parallel Agents ↗ Splits independent investigations into bounded agent assignments and checks their integration afterward.](/skills/obra-dispatching-parallel-agents/)[### Gradio App Builder ↗ A Gradio reference and example collection for building Python interfaces, event-driven layouts and chat demos.](/skills/huggingface-huggingface-gradio/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/) ## Continue your investigation - [Choose a toolkit](/tools/) - [Inspect execution hosts](/agents/) - [Check tool access](/mcp-servers/) - [Check project dependencies](/check-repo/)