jwilger

jwilger/ai-plugins

Plugin Claude Code

A multi-harness marketplace of AI coding-assistant plugins for Claude Code, Codex, and other harnesses that support the plugin concept.

jwilger/ai-plugins

Instructions file CodexOpenCode

AGENTS.md instructions for jwilger/ai-plugins, covering agents.md, what this repo is, development environment, worktree workflow and backlog management.

jwilger/ai-plugins

Instructions file

Claude Code instructions for jwilger/ai-plugins: This file intentionally defers to the harness-agnostic guide. Read it.

jwilger/ai-plugins

Plugin Claude Code

John's consolidated development workflow, engineering standards, worktree, task, review, and agentic-system tooling.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when the user asks to shape fuzzy planning, product/design/engineering tradeoffs, scope/spec/ticket plans, or says "challenge this/help me think"; delegate to an advisor subagent. Good for rough ideas, second opinions, load-bearing decisions, or scope cuts. Skip scoped implementation, narrow bugs, reviews, and…

jwilger/ai-plugins

Plugin Claude Code

agentic-systems-engineering. Multi-harness marketplace of AI coding-assistant plugins for Claude Code, Codex, and related agentic development tools.

jwilger/ai-plugins

MCP server Claude CodeCodexCursor +2

MCP server "promptfoo" as configured in jwilger/ai-plugins. Launched with ./bin/promptfoo-mcp.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when planning or delivering an LLM or agentic-system project, especially for experiment loops, walking skeletons, demos, data stories, scope control, and release-readiness evidence.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when designing, implementing, reviewing, or debugging LLM-backed or agentic systems, including prompts, structured outputs, tool use, RAG, agent loops, orchestration, observability, security, cost/provider routing, and AI delivery plans.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when evaluating prompts, LLM features, agents, RAG, judges, tool-use policies, or any stochastic behavior where one successful run is not reliable evidence.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when setting up a project-local eval harness for prompts, agents, judges, RAG, tools, or other LLM behavior, especially when the default should be free/OSS promptfoo with repo-owned artifacts.

jwilger/ai-plugins

Plugin Claude Code

babysit-pr. Multi-harness marketplace of AI coding-assistant plugins for Claude Code, Codex, and related agentic development tools.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when a pull request or merge request needs to be driven to merge — monitoring current-head checks, classifying failures, handling review threads, and merging only after repository-required gates, across GitHub, Forgejo, or GitLab.

jwilger/ai-plugins

Plugin Claude Code

development-discipline. Multi-harness marketplace of AI coding-assistant plugins for Claude Code, Codex, and related agentic development tools.

jwilger/ai-plugins

Agent

Read-only helper for bounded inventory, extraction, classification, and mechanical transformation tasks with an independently verifiable result.

jwilger/ai-plugins

Agent

Read-only strong-reasoning reviewer for architecture, security, human-safety, ambiguity, disputed verification, and readiness analysis.

jwilger/ai-plugins

Agent

Read-only strong-reasoning implementation planner that prepares isolated service requests.

jwilger/ai-plugins

Agent

Read-only implementation planner that prepares structured workspace-editor requests.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when preparing to edit a feature, bug fix, refactor, documentation or configuration update, packaging or release work, migration, operational change, or other substantive repository change; classify it before editing and explicitly decide all ten surfaces from repository or supplied evidence.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when a pushed CI run fails or before later work or pushes; coordinate multiple agents through Tiber's CI-recovery owner/lease, reproduce the exact recovery record, permit only a causal repair or unchanged-SHA rerun, and require terminal success.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when choosing whether and how verified work should be committed, pushed, reviewed, and delivered under a repository's local workflow policy; local-only mode does not authorize a commit unless the user or repository requires one.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when a development request needs lifecycle routing for diagnosis, implementation, review feedback, PR or MR creation, readiness, CI failure, verification, or delivery.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when completing or claiming readiness for local-only changes, a branch, pull request, merge request, or merge-to-main; final review applies even when repository policy forbids publishing, including scope growth, proposed work splits, and medium-risk review-budget checkpoints.

jwilger/ai-plugins

Skill Claude CodeCodex

Use when selecting a model for delegated coding work or when a development workflow must escalate a helper to stronger reasoning.