JoshuaOliphant

JoshuaOliphant/claude-plugins

Plugin Claude Code

Plugin marketplace listing 10 plugins: mochi-creator, autonomous-sdlc, hexagonal-agents, compound-knowledge, autoloop.

JoshuaOliphant/claude-plugins

Instructions file

Claude Code instructions for JoshuaOliphant/claude-plugins, covering claude.md, project overview, repository structure, plugin inventory and key architectural concepts.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when starting debugging, planning features, encountering errors, making design decisions, or working in unfamiliar code. Searches past solutions and engineering principles captured by compound-capture to surface institutional knowledge and prevent repeated mistakes. Trigger phrases include "have we seen this…

JoshuaOliphant/claude-plugins

Plugin Claude Code

Small, composable workflow skills for coding agents: docs-first discipline, autonomous execution, cross-agent watchdog and plan arbitration, efficient model orchestration, clear status recaps, usage-limit awareness, and local self-contained HTML visual plan/recap modes.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a session ID, Claude Code session/transcript, PR, branch, log, or run summary.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use always when operating as Claude Fable on codebase-heavy or token-heavy work: Fable orchestrates, architects, synthesizes, and judges while cheaper subagents do bounded research, coding, testing, and log reduction.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use whenever running a high-cost frontier model on codebase-heavy or token-heavy work (apply automatically on such models): delegate research, coding, testing, and log reduction to cheaper subagents, reserving the expensive model for planning, tradeoffs, synthesis, and final review.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Save agent-skills workflow feedback proactively. MUST trigger when the user corrects how a visual plan/recap, recap status block, orchestration, autonomy, docs-first, or review skill behaves ("recaps are too long", "always web-search the docs first", "don't stop to ask", "plans should lead with the wireframe") or…

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going until done", "finish while I am away", "do not ask questions unless truly blocked", or similar. Convert ordinary ambiguity into stated assumptions, proceed…

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when the user wants every response to end with a clear status signal — "give me a status line", "use the red/yellow/green convention", "end with a recap" — or when installing the managed AGENTS.md/CLAUDE.md status-block instruction.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs, fast-moving product behavior, user requests for latest/current/official behavior, unfamiliar repo docs/specs, errors that may indicate API drift…

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use before substantial work and between parallel agent waves — especially overnight batch runs or multi-wave parallel subagents that might exhaust the 5-hour or weekly usage window — to check usage, pause near the cap, and resume only when the window is clear.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when turning a plan into a self-contained interactive HTML document (diagrams, file maps, annotated code, wireframes, open questions) saved locally and opened in the browser — no account or external service.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

Use when turning a PR/branch/commit diff into a self-contained interactive HTML recap (annotated diffs, file maps, API/schema summaries, wireframes) saved locally and opened in the browser.

JoshuaOliphant/claude-plugins

Plugin Claude Code

Generate autonomous experiment loops with immutable runner scripts, tiered quality gates, secondary metrics, and structured METRIC output.

JoshuaOliphant/claude-plugins

Agent

Explore a project directory to identify build system, test commands, source files, and candidate metrics for an autoloop experiment.

JoshuaOliphant/claude-plugins

Skill Claude CodeCodex

MUST use when the user wants autonomous, iterative optimization — letting Claude run experiments unattended. Trigger: "autoloop", "autoresearch", "experiment loop", "hill-climbing", "optimize overnight", "karpathy loop", "let Claude optimize while I sleep", "automate trying different approaches", "set up a loop to…

JoshuaOliphant/claude-plugins

Plugin Claude Code

Autonomous SDLC as a state machine on disk driven by a Stop-hook loop (optionally a user-armed /goal) — one verified unit of work per iteration, decide-log-proceed autonomy, built-in verify/code-review/simplify gates.

JoshuaOliphant/claude-plugins

Agent

Strategic architect that explores codebases, creates plan documents, and decomposes work into tasks with dependencies.

JoshuaOliphant/claude-plugins

Agent

Focused execution agent that implements ONE task at a time with PostToolUse validation hooks for automatic quality enforcement.

JoshuaOliphant/claude-plugins

Command

Quickly understand a codebase before starting work - reads structure, key docs, and summarizes understanding.

JoshuaOliphant/claude-plugins

Command

Stop an active SDLC loop cleanly — sets BLOCKED(cancelled) so the driver releases, then cleans up.

JoshuaOliphant/claude-plugins

Command

Show the state of the SDLC loop — current state, iteration budget, decisions, progress.