Parallelizes only work proven safe by compiling resource-aware atomic plans for builds, tests, Make/Compose workflows, and long-running jobs with live progress and measured savings.
Review & TestingNo.047AI code reviews grounded in six classic engineering books — decay risk diagnostics with book citations, severity labels, and four analysis modes (PR review, architecture audit, tech debt, test quality).
Review & TestingNo.057Use ChatGPT as a reviewer, advisor, editor, or implementer in Codex, with ZIP packets by default and an opt-in MCP bridge.
Review & TestingNo.068Turn software intent into one approved contract, then let AI build and verify in one shot—with traceable evidence for each requirement.
Review & TestingNo.069Responsibility-flip mode for when the user cannot review the output: irreversible steps first, one verification step, every default named with its alternative, at most three questions only the user can answer.
Review & TestingNo.071Local-first acceptance gate that checks coding-agent scope, sensitive surfaces, deterministic analyzers, and repository verification from immutable Git snapshots, then writes signed receipts before the PR.
Review & TestingNo.083Run long local builds, tests, benchmarks, and inference jobs as durable detached processes with tracked status, bounded results, and completion delivery across Codex surfaces.
Review & TestingNo.087Second-pass review of Claude-driven plans and implementations.
Review & TestingNo.090Codex plugin and Skill that stages verified desktop skin packs from GitHub releases, validates files, and keeps restore guidance visible.
Review & TestingNo.119Team workflow skills for specs, plans, TDD, debugging, verification, review, branch finishing, and design context.
Review & TestingNo.127Stop hook that blocks "fixed/done" claims when no test output or exit code appeared in that turn (Claude Code & Codex, MIT).
Review & TestingNo.128Verified-inventory agentic commerce over a hosted MCP server, with merchant and product discovery, agent-initiated checkout, and onchain brand, credit-risk, and repayment attestations.
Review & TestingNo.130Bounded-autonomy plugin that asks only the decisions that belong to the user, builds nothing before the intent is approved, verifies with checks that actually ran, and keeps project decisions as plain Markdown across Codex, Claude Code, Grok Build, Copilot CLI, and Antigravity CLI.
Review & TestingNo.140Finds tests that stay green when the code they cover is broken, applying six ordered judgments over Python, TypeScript, JavaScript, and Robot Framework suites in Codex CLI and Claude Code.
Review & TestingNo.154Drives a live Godot 4.x editor through the low-token Hera CLI — scene, node, and signal edits, play control, and runtime QA with verifiable compact JSON output, with the companion addon published on the official Godot Asset Store.
Review & TestingNo.175Goal-based planning and proof gate for Codex and Claude Code that turns requests into ownership, cutover, review-gate, and acceptance-evidence plans.
Review & TestingNo.192Temporary inboxes for Codex — OTP, magic links, signup QA, simulate-first autotests (23 MCP tools).
Review & TestingNo.193Evidence gates for AI-generated pull requests that catch stale issues, overlapping work, and unsupported test claims.
Review & TestingNo.217Paper discovery, citation verification, graph exploration, and DeepScan analysis.
Review & TestingNo.237Agentic PR review: hybrid RAG + code graph via MCP, review skills for Codex.
Review & TestingNo.240Prove suspected bugs with a red-green-red test loop: verify the cause, watch the test fail, apply the fix, and confirm the test fails again when the fix is reverted.
Review & TestingNo.243Deliberate context compaction within a single Codex thread on the VS Code extension, with a verified task handoff and one-time automatic continuation.
Review & TestingNo.247Snapshots each Codex session and stops the agent when it weakened tests, suppressions, or CI gates, once per signal; local and deterministic.
Review & TestingNo.277Three-phase Requirements → Design → Tasks workflow for Claude Code and Codex — EARS notation acceptance criteria, autonomous execution loop, cross-spec dependencies, and post-implementation acceptance testing.
Review & TestingNo.288Evidence-gated Codex loop harness with specialist skills, including near-pixel authorized website cloning backed by screenshots, assets, build output, and visual QA.
Review & TestingNo.295Hook-powered test generation -- detects files changed during an agent turn and instructs Codex to write and run tests automatically. Zero config, 8 languages.
Review & TestingNo.297Install and verify revenue-first website analytics from Codex, connect payment attribution, and identify which traffic sources and customer journeys become revenue.
Review & TestingNo.341Decompose broad project briefs into researched plans and implement sectioned work with TDD, quality gates, and traceability.
Review & Testing