build-until-agreed

Solid

Builds toward a goal agreed up front, then has independent read-only auditors judge whether it is actually met — looping build → blind audit → verify → fix until the harness passes, no verified blocking finding remains, and more than half of the auditors agree the goal is met. Starts from the user's problem, not the feature: writes a short contract (who hurts, acceptance criteria, harness command, declared decisions, severity bar, round budget) before any code. Auditors never see each other, earlier rounds, or the builder's reasoning; every blocking finding is re-checked by a separate verifier before anything is fixed, so deliberate trade-offs and unreproducible claims don't drive churn. Keeps a per-round ledger, prefers cutting to adding, stops and hands back on thrash or the round cap, and can finish with an external review-bot gate. Never merges. Use for long-running or exploratory builds, boilerplates, or any change where "done" should be checked by someone other than the builder.

AI & Automation 4 stars 0 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
23
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Build Until Agreed The builder is the worst judge of whether the work is done. This skill writes down what "done" means *before* building, then lets independent auditors decide — and checks their claims before acting on them. **Standing rules — they hold for the whole run, every round:** 1. **Problem first.** No contract without a named user and the pain it removes. If there isn't one, say so and stop — we don't build for the sake of building. 2. **Auditors are blind and read-only.** Fresh, **unnamed**, never `fork` — each round. They get the contract file, the commit range and the harness — never the ledger, the builder's reasoning, earlier findings, or each other's verdicts. The ledger is git-ignored, so no commit range can show it to them. 3. **Nothing is fixed until it is verified.** A blocking finding is a claim until a separate verifier reproduces it. Documented decisions are not defects. 4. **Freeze while auditing.** Commit before a round; no edits until every auditor returns. 5. **Prefer cutting to adding.** Before each fix, name what it protects. If nothing, cut. 6. **Never merge. Never push to the default branch.** Work on a branch; the human merges. This is enforced here, in the workflow — `Bash(git *)` does not enforce it. 7. **Explain progress.** After every round, print the round block (see `reference/contract-and-ledger.md`) so the user always knows where things stand and why. ## Preferences _On startup, use Read to load `~/.claude/s...

Details

Author
mostafa-drz
Repository
mostafa-drz/claude-skills
Created
7 months ago
Last Updated
yesterday
Language
HTML
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

build

Implement a planned change in thin vertical slices, test-first, with atomic commits and four mandatory exit gates. Use when you say `build this`, `implement this slice`, or `write the code for this task`, and run it after plan. Do NOT use to decide what to build (use spec) or to sequence the work (use plan), and do NOT use to review a finished diff (use review).

47 Updated today
rjmurillo
AI & Automation Listed

build-loop

Drive a build to actually-works, near-finish-line craft by looping build → see → exercise → check → critique → rebuild over the agent's existing tools (bash build/test, headless screenshot + vision, Playwright, axe/Lighthouse) until acceptance criteria pass or an explicit stop-condition fires — no infinite thrash. ALWAYS invoke when the user says any of "tighten this build", "iterate until it passes", "self-verify the UI", "make it actually work, not just compile", "loop until the core flows pass", or "drive this to near-finish-line". Also invoke proactively after a scaffold or feature lands and before handing a draft to a human. Composition-first over existing tools, not a new program; it states its own honest bounds — objective craft only, taste self-graded, ~80% ceiling, market validation out of scope. Do NOT use to decide WHAT to build (that's ideate) or whether a design/strategy is sound (deep-dive).

84 Updated 1 months ago
nelsonwerd
AI & Automation Listed

brain-build

The autonomous build contract, out of the box — "/brain-build <what you want>" activates the disciplined hands-off build power users used to hand-write a standing prompt for. Use when the user says "/brain-build", "brain build", "build this autonomously", "build this hands-off", "loop until it's done", "don't ask me, just build it", or asks for an unattended/self-grading build. Phase-gated per rUv's SPARC, self-verified and self-graded /100 against a per-phase rubric (below 95 → fix and regrade, max 5 iterations), cost-tier routed with printed receipts, crash-resumable via checkpoints, questions batched into one list — the user writes the goal, not the contract.

70 Updated today
stuinfla