Toolshed — Testing skill for Claude Code
Agent tooling for Claude Code and Grok.
How to install Toolshed
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open uddipan978/toolshed and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Toolshed does
Agent tooling for Claude Code and Grok. Home of foreman — a plugin that drives a requirement through a gated SDLC (grill → plan → critique → build → test → beta → handoff) by spawning and supervising independent worker sessions with budgets, deadlines, stuck-detection and handover compaction.
Alternatives in Testing
- Spec Driven Development — Drive Kandev feature work through spec, plan, independent tasks, implementation, QA, and verification 697 ★
- Superpowers Evals — Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Ge 107 ★
- Pi Task — Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→researc 81 ★
README
toolshed
Claude Code / Grok / Codex plugins. Each plugin is a self-contained directory with its own `.claude-plugin/` manifest, README, license and tests.
| Plugin | What it does | Install |
|---|---|---|
| foreman | Agentic SDLC orchestration — a manager session spawns and supervises worker sessions through gated lifecycle phases. | claude plugin marketplace add /foreman && claude plugin install foreman@claude-tooling --scope user |
| hld | Human-Like Design — a gated UX/UI studio: grill once, research with a kill door, IA-derived wireframes, contract-based anti-slop, nine-viewport proof. Standalone, or defers to foreman when one is present. | claude plugin marketplace add /hld && claude plugin install hld@hld --scope user |
`` is this checkout's path, e.g. `/Users/shankhajeettaran/workspace/experiments/toolshed`.
Both plugins are MIT licensed (per-plugin LICENSE files). HLD absorbs foreman's four worker-contract formats (MIT, SHA-pinned in [hld/CREDITS.md](hld/CREDITS.md)); the foreman engine itself is not duplicated — HLD detects a runnable foreman at plan time and defers to it.
Related Skills
Pharn Loop
Run the PRODUCT pipeline as a BOUNDED, FLOOR-GATED auto-iteration: the same gated chain as /pharn-ship (/pharn
AI Native Sdlc Skills
Unofficial Claude Code skills adapted from Anthropic's The AI-Native SDLC playbook — the committed-artifact ch
Pharn Verify
Verify a built feature CORRECTLY in the USER's codebase through two cleanly-separated layers — the sixth produ
Manual QA
Generate a manual QA procedure from this session's changes and walk through it interactively. The user drives
Spec Research
Investigate a loose idea before committing to a change. Runs codebase + (optional) web research via subagents,
V Epic
Drive an EPIC — chain several features into one autonomous, resumable, dependency-ordered build on a single br
Related Agents
Gamedev Orchestrator
Orchestrates LibreGameDev Grok skills — feel, critique, playtest, engines, input, saves, performance, ethics.
Synthesis Orchestrator
Orchestrates LibreUIUX Grok skills for a production-ready UI pass — principles, critique, a11y, responsive, br
Sdlc Coder
Drives strict TDD (Red→Green→Refactor) implementation of one story file, in the target repository. Always load