Constraint-Driven Development Skill: guardrails an agent cannot weaken

DemoReal run · claude-sonnet-5-5 · October 2026

Set up quality constraints for our project (fictional example). Facts you may rely on instead of asking: TypeScript 5, Vitest, Biome for lint, GitHub Actions CI, the web app has a preview URL on every PR, AGENTS.md exists, project coverage today is 58.2%, bundle is 212 kB. I know this is normally an interview, so here are my answers: Q1 pick coverage, security scanning and accessibility; Q2 block on the floor, warn on the rest for two weeks; Q3 measure where we are and hold it; Q4 90 seconds. Write CONSTRAINTS.md in the current folder and tell me what to install and wire up. Then check this agent-made diff against the floor and tell me what it violates: ``` --- a/src/cart.test.ts +++ b/src/cart.test.ts @@ - it('rejects negative quantities', () => { expect(() => addItem(-1)).toThrow(); }); + it.skip('rejects negative quantities', () => {}); --- a/src/pay.ts +++ b/src/pay.ts @@ + // @ts-ignore + const total: number = order.total; + try { await charge(total); } catch {} --- a/CONSTRAINTS.md +++ b/CONSTRAINTS.md -| Coverage | Changed lines >= 80% covered | vitest | task end | +| Coverage | Changed lines >= 60% covered | vitest | task end | ```

Skill: constraint-driven-development

I wrote CONSTRAINTS.md in the current folder. There is no AGENTS.md here, so I didn't add the pointer line to it. In your real repo, add this line to AGENTS.md: Read CONSTRAINTS.md before writing code. Do not weaken it to make a change pass.

What's in it

Floor (blocks now): no new suppressions, no stubs or empty catch, no skipped or deleted tests, no stripped assertions, no secrets, and no weakening the file itself.
Warn until 2026-10-24, then block: types, lint, changed-line coverage ≥ 80%, Semgrep, osv-scanner and axe.
Held, not enforced: project coverage stays at 58.2% (0.5% tolerance) and the bundle stays at 212 kB.
Budget: checks at task end must finish in 90 seconds. Semgrep, osv-scanner and axe run in CI or on the preview deploy.
Performance budget: you didn't pick one, so bundle size is only tracked. I picked 80% for changed-line coverage myself, because you asked to hold the current level and 80% is the skill's default for new code. Say so if you'd rather not have it.

What to install and wire up

You already have tsc, Vitest and Biome.

Tool	Install
Coverage	`npm i -D @vitest/coverage-v8`, with the `lcov` reporter on
gitleaks	`brew install gitleaks`
Semgrep	`pipx install semgrep`
osv-scanner	`brew install osv-scanner`
axe	`npm i -D @axe-core/cli`

Add these scripts to package.json:

"check:fast": "tsc --noEmit && biome check . && gitleaks detect --redact --no-banner",
"check:task": "npm run check:fast && vitest run --coverage",
"check:full": "npm run check:task && semgrep scan --config p/default --config p/owasp-top-ten && osv-scanner scan source -r ."

After each edit: run check:fast, for example from an agent post-edit hook.
At task end: run check:task. Compare the lcov it writes against git diff for the 80% changed-line check, without running the tests a second time.
In GitHub Actions: run check:full on every PR. After the preview deploy, run axe $PREVIEW_URL --tags wcag2a,wcag2aa,wcag21aa.
Floor guard: it needs no installs and only reads the diff. Adapt the reference implementation in the skill's references/floor-guard.md, which I haven't opened.
gitleaks: always use --redact, so a leaked key never lands in a transcript.

The diff against the floor

It violates the floor in four places, and one of them also edits the constraints file.

cart.test.ts: it.skip adds a skipped test, and the assertion expect(...).toThrow() is stripped. Nothing in the diff gives a reason in a commit message. The negative-quantity rule is no longer tested.
pay.ts, // @ts-ignore: this is a new suppression. It hides a type problem on order.total that should be fixed.
pay.ts, catch {}: this is an empty catch around charge(total). A failed payment now passes silently and the code carries on as if it worked. This is the most dangerous change in the diff.
CONSTRAINTS.md: the changed-line coverage threshold drops from 80% to 60% in the same change as the code it would excuse. That breaks the rule against weakening the file.

The four edits fit one pattern: the agent hit red checks and took the cheapest route to green. Reject the diff. The agent should restore the test, fix the type of order.total, handle or rethrow the charge error, and put the threshold back at 80%.

Test run with the interview answers given up front, because the Skill does not run its interview in non-interactive mode. The model wrote CONSTRAINTS.md in a temporary folder, listed what to install, and correctly found four floor violations in a sample diff. It chose the 80% coverage figure itself and said so, and it did not open the floor-guard reference file. Nothing was installed.

What it does

Runs a short interview (stack, current baseline, checks you already have, what the agent is allowed to change), then writes a CONSTRAINTS.md. It has a floor that blocks from day one (no new suppression comments, no stubs or empty catch blocks, no skipped or deleted tests, no stripped assertions, no secrets, no weakening the file itself), numeric rules with a named tool and a run point for each (types, lint, secrets, changed-line coverage, code and dependency security, accessibility), a ratchet that holds today's numbers instead of raising them, a time budget for the agent's own checks, and an exceptions table with owners and expiry dates. New rules start as warnings with a switch-to-block date. It lists what to install and which scripts to add, and it can review an agent's diff against the floor.

Output

A CONSTRAINTS.md, install and wiring instructions, and (on request) a verdict on a diff.

Good for

Teams letting an agent write code who want the checks to be something the agent cannot rewrite to get a green result.

Notes & risks

Medium risk: the Skill itself is instructions only (plus a reference file for a floor-guard script), but it tells the agent to write CONSTRAINTS.md and to suggest installing tools (coverage, gitleaks, Semgrep, osv-scanner, axe) and adding scripts or hooks to your project. Review those commands before running them. Test-run once with the interview answers supplied up front, since the interview does not run in non-interactive mode: it wrote the file in a temporary folder, listed the installs (nothing was installed) and found four floor violations in a sample diff. It picked the 80% figure itself and said so; it did not open the floor-guard reference. By Addy Osmani, MIT.

SKILL.md original3 files in this package