By mikersays
Lightweight markdown-based tracker for bugs, features, chores, and todos that lives in docs/plan/ inside your repo
Create a new planning item (bug, feature, chore, or todo) as a markdown file inside docs/plan/. Use this whenever the user wants to track a new bug, feature, todo, follow-up, issue, or piece of deferred work in their repo — including phrases like "log this", "track this", "remember to", "I need to fix", "open an issue for", or any "we should do X later" request. Auto-initializes docs/plan/ if it doesn't exist yet.
Close (mark done) a planning item in docs/plan/. Use whenever the user finishes work on a tracked bug/feature/chore/todo — phrases like "I fixed it", "that's done", "ship that off", "close item 7", "mark X complete", "wrap up the search ticket" all trigger this. Sets status to done and stamps the closed date. The file is not deleted or moved — closed items stay in docs/plan/ as the history record.
Bootstrap a docs/plan/ folder in the current repo for tracking bugs, issues, chores, and todos as markdown files. Use this whenever the user wants to start a lightweight planning system, set up local issue tracking inside a repo, or asks for a "plan folder" / "todo tracker" / "issues directory" — even before they've used any other /plan-* command. /plan-add will auto-init if missing, so this command is primarily for explicit setup.
List planning items in docs/plan/, optionally filtered by status, type, priority, due date, or tag. Use whenever the user wants to see open issues/bugs/todos, check the status of planned work, find overdue items, or get an overview of what's in the plan folder. Phrases like "what's open", "what's due", "show me bugs", "list todos", "what's in the plan", "show overdue work" all trigger this. The default view hides done items.
Update an existing planning item in docs/plan/ — change its status, priority, due date, type, tags, or append a dated note. Use whenever the user wants to mark something in-progress, change a deadline, raise/lower priority, unblock something, retitle, or add a comment/note to a tracked item. Accepts either the numeric ID or a slug fragment from the title. Phrases like "start work on 7", "push X to next week", "mark item Y blocked", "add a note to the search ticket" all trigger this.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A marketplace of plugins for Claude Code and Codex CLI.
/plugin marketplace add mikersays/mikersays-plugins
Then install any plugin:
/plugin install ship@mikersays-plugins
Native (recommended):
codex plugin marketplace add mikersays/mikersays-plugins
codex plugin add ship@mikersays-plugins
Repeat codex plugin add <plugin>@mikersays-plugins for each plugin you want.
Headless (one-liner):
curl -sL https://raw.githubusercontent.com/mikersays/mikersays-plugins/master/INSTALL.md \
| codex exec --full-auto --add-dir ~/.codex --add-dir ~/.agents --skip-git-repo-check -
Interactive — paste this prompt into a Codex session:
Read https://raw.githubusercontent.com/mikersays/mikersays-plugins/master/INSTALL.md and follow the instructions exactly to install the mikersays-plugins marketplace on this machine. Create or update the local marketplace file and hooks config, verify the install, and tell me the final result.
The headless/interactive methods clone the repo to ~/.codex/plugins/mikersays/mikersays-plugins, symlink skills into ~/.agents/skills/, register all plugins in ~/.agents/plugins/marketplace.json, and install a SessionStart hook that auto-updates the marketplace on every Codex startup.
| Plugin | Description | Usage |
|---|---|---|
| ship | Git commit and push in one command | /ship [message] |
| tech-writer | Review and rewrite docs using Google's Technical Writing guidelines | /tech-writer [file path] |
| deck | Generate a self-contained HTML slide deck from a topic | /deck [topic] |
| roadmap | Generate a visual HTML Gantt-chart roadmap from a markdown file | /roadmap [file] |
| diagram | Generate interactive SVG diagrams from a description | /diagram [description] |
| monograph | Build a multi-page PhD-level GitHub Pages site on any topic, with research, free-licensed photography, and a topic-tuned design — shipped to docs/ via parallel expert subagents | /monograph [topic] |
| bootcamp | Swarm of expert subagents builds an interactive zero-to-hero course site — modules, worked examples, exercises with solutions, checkpoints, a capstone, and progress tracking — shipped to docs/ and deployed on GitHub Pages | /bootcamp [topic] |
| pr | Create a GitHub PR with auto-generated title, summary, and test plan | /pr [title] |
| plan | Track bugs, features, chores, and todos as markdown in docs/plan/ | /plan-init /plan-add /plan-list /plan-update /plan-close |
| issues | Per-issue bug/feature/incident tracker in docs/issues/ with symptom/repro/root cause/fix/verification, branch-on-start, and an alignment-before-implement rule | /issue-init /issue-new /issue-start /issue-close |
| handoff | Audit session context and persist what matters for the next agent | /handoff |
| maintenance | Sync docs, run installer, run uninstaller | /sync-docs /install-marketplace /uninstall-marketplace |
plugins/<name>/.claude-plugin/plugin.json and .codex-plugin/plugin.json (name, description, version; codex also needs "skills": "./skills/" and an interface object)skills/<skill-name>/SKILL.md (optionally add agents/openai.yaml for Codex UI metadata)README.md for documentation/sync-docs (from the maintenance plugin) to register the plugin across all three marketplace files, INSTALL.md, UNINSTALL.md, and docs/index.htmlpython3 scripts/validate.py to confirm consistency. Enable the pre-commit hook once per clone with git config core.hooksPath .githooks so this runs automatically.npx claudepluginhub mikersays/mikersays-plugins --plugin planStage, commit, and push all changes in one step, with auto-generated message if none given
Review and rewrite documentation in place using Google's Technical Writing guidelines
Generate a self-contained interactive HTML Gantt chart from a markdown roadmap file
Create a GitHub PR for the current branch with auto-generated title, summary, and test plan
Generate an interactive SVG diagram (architecture, sequence, flowchart, ER) from a description
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).