prime-radiant-inc

prime-radiant-inc/sprout

Agent

Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.

prime-radiant-inc/sprout

Agent

Implement a single task from a plan: write code, write tests, commit, and report status.

prime-radiant-inc/sprout

Agent

Review implementation code quality: cleanliness, testing, maintainability, and design.

prime-radiant-inc/sprout

Agent

Review whether an implementation matches its task specification — nothing more, nothing less.

prime-radiant-inc/sprout

Agent

Private sidecar commentator for the human; watches root sessions without steering them.

prime-radiant-inc/sprout

Agent

Ask to run shell commands — build, test, install, git, or any CLI tool — and get back execution findings.

prime-radiant-inc/sprout

Agent

Ask to create named files or make targeted edits — acts directly when targets are decisive, reads only when context is missing.

prime-radiant-inc/sprout

Agent

Ask to interact with external services via MCP (Model Context Protocol) — list available servers, discover their tools, and call them with arguments.

prime-radiant-inc/sprout

Agent

Ask to manage project memory documents — list, read, write, or search .md files in the project memory directory.

prime-radiant-inc/sprout

Agent

Ask to find and read specific files or search for patterns — returns extracted information, not raw dumps. Use for quick targeted lookups, not broad exploration.

prime-radiant-inc/sprout

Agent

Ask to track work items for this session — create tasks, list them by status, update progress, assign to agents, and add comments.

prime-radiant-inc/sprout

Agent

Analyze agent execution transcripts — answer questions about tool usage, reasoning, turns, parallel calls, stumbles, and behavior patterns.

prime-radiant-inc/sprout

Agent

Ask to fetch web pages, call REST APIs, or download data from URLs — parses responses and extracts relevant content.

prime-radiant-inc/sprout

Agent

Verify that work is complete by gathering fresh evidence — run tests, check requirements, confirm claims.

prime-radiant-inc/superpowers-evals

Instructions file CodexOpenCode

AGENTS.md instructions for prime-radiant-inc/superpowers-evals, a project described as: Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA agent and grades them on workflow compliance against scenario criteria and…

prime-radiant-inc/superpowers-evals

Instructions file

Claude Code instructions for prime-radiant-inc/superpowers-evals, covering superpowers evals, canonical actors, commands, architecture and scenario conventions.

prime-radiant-inc/streamlinear

Plugin Claude Code

Streamlined Linear integration - one tool, seven actions, zero bloat.

prime-radiant-inc/streamlinear

Skill Claude CodeCodex

Manage Linear issues. Use when asked about tasks, tickets, bugs, or Linear.

prime-radiant-inc/streamlinear

Instructions file CodexOpenCode

Instructions for prime-radiant-inc/streamlinear, covering agents.md, project, setup, verification and build artifacts.

prime-radiant-inc/streamlinear

Instructions file

Instructions for prime-radiant-inc/streamlinear, covering claude.md, what this is, setup, common commands and build artifacts.

prime-radiant-inc/gauntlet

Skill Claude CodeCodex

Use when writing or reviewing a Gauntlet story card. Establishes the calibration framing — outcomes, persona binding, observable acceptance criteria — and explicitly rules out wrong-shaped frames (Agile user stories, QA step-scripts, BDD Given/When/Then) so prior knowledge does not contaminate the card.

prime-radiant-inc/stockyard

Instructions file

Claude Code instructions for prime-radiant-inc/stockyard, covering stockyard development guide, building, deploying (linux), testing and project structure.

prime-radiant-inc/parallel-adversarial-review

Plugin Claude Code

Two skills for adversarial code review. parallel-adversarial-review dispatches two same-model reviewer subagents in parallel under a competitive scoring frame, aggregating findings and taking the worst severity on disagreement. multi-model-adversarial-review extends this to N installed coding-agent CLIs (claude, codex.

prime-radiant-inc/parallel-adversarial-review

Skill Claude CodeCodex

Use for high-stakes review where you want multiple model providers reviewing the same artifact and critiquing each other. Shells out to installed coding-agent CLIs (claude, codex, gemini, pi, opencode by default; amp and droid available opt-in) to run parallel reviews, then runs a cross-critique grid where each…