SKILL verified MIT Self-run

Build

Name: Build
Availability: InStock
Author: artttj

skill-artttj-rapid-stack-build · by artttj

Use when executing work — a signed-off plan (gate mode) or a routed small fix (direct mode). TDD, capped review, verification, proof.

↗ Website ↗ Repository

— No reviews yet

0 installs

38 views

0.0% view→install

Install

$ agentstack add skill-artttj-rapid-stack-build

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

✓ Prompt-injection patterns
✓ Secret / credential exfiltration
✓ Dangerous shell & filesystem operations
✓ Untrusted network calls
✓ Known-malicious package signatures

What it can access

✓ Network access No
✓ Filesystem access No
✓ Shell / process execution No
✓ Environment & secrets No
✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

Links to your public security report.

[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-artttj-rapid-stack-build)

Reliability & compatibility

✓ Security review passed

0 installs to date

— no reviews yet

● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →

Are you the author of Build? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.

About

op:build

Preconditions (gate mode)

plan.md has status: signed-off.
Recompute the spec pin and compare with the plan's spec-version:

awk 'c==2{print} /^---$/{if(c/spec.md | shasum -a 256 | cut -c1-12

Mismatch → hard stop, arrow-choice: re-run /op:plan / proceed anyway (the final report then records "pin overridden").

Steps

Iron law first: quote one real convention (file:line) from the repo before any new code.
Branch (arrow-choice): current branch / new feat/ / isolated worktree via superpowers:using-git-worktrees.
Execute:

Plan with ≥3 tasks → superpowers:subagent-driven-development over plan.md.
Smaller plan → inline, superpowers:test-driven-development per task.
Direct mode (no plan, routed small fix): one TDD cycle — failing test, minimal fix, green.
superpowers absent → inline fallback: write the failing test, run it, implement minimally, run to green, commit per task.

Review, capped at 3 rounds: dispatch the rs code-reviewer agent on the diff (rs absent → a fresh general subagent prompted for high-confidence defects only). Fix what is real, push back with a reason on what is not, stop at the cap.
Verify: superpowers:verification-before-completion — run the recipe test command (or the repo's test command), read the output, report it as it is.
Gate-mode close: set spec status: implemented, commit the status flip with the work. Offer /op:ship (arrow-choice).

Proof at end: test output, git diff --stat, status line.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Author: artttj
Source: artttj/rapid-stack
License: MIT
Homepage: https://artttj.de/blog/thirteen-commands/

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

v0.1.0 Imported from the upstream source.