genesis-tools

Plugin genesis-tools from marketplace genesis-tools in genesiscz/GenesisTools. Commands read from the repo's manifest — yesterday.

Skills (35)

• agents-talk

  Claude and Grok only. Picks the channel when agents must talk WHILE they work: a gt:handoff-to swarm, or a Claude Code agent team whose lead may need to steer a busy teammate (native team mail waits until the teammate's turn ends). Uses the tools agents bus with a real push monitor. NOT for ordinary

• gt:analyze-har

  Token-efficient HAR (HTTP Archive) analysis with a reference system. Use for any .har file, analyzing network traffic, debugging API calls, or reviewing HTTP requests. Never cat/jq HAR files — always use this.

• artifact

  Create, serve, and build LOCAL dashboards and HTML artifacts via `tools artifact` — a single .tsx or .html file anywhere (no folder, no node_modules, no tsconfig) becomes a live page with clean URLs, React, Tailwind and a 60+ component kit (Tabs, Router, MdViewer, Mermaid diagrams, DiffView, TreeVie

• gt:azure-devops

  Azure DevOps work items, queries, dashboards, sprints, wiki pages, comments, history, parent chains, and Test Plans (plans, suites, test cases with steps, test points and outcomes). Use for "get workitem", "fetch task", "show query", "analyze task", "show the test plan", "add a test case", or any Az

• gt:browser-router

  Trigger only on /browser-router. Create routing for any links that are not ordinary web URLs, so a click on this Mac runs the saved route instead of opening a page.

• chrome-devtools

  Drive the user's real Chrome or Brave over the DevTools Protocol with `tools chrome-devtools`: auth and SSO redirect loops, cookie and session bugs that happen only in their browser, HAR capture and their open Network tab, CORS and local-network blocks. Also use it for front-end performance and live

• gt:claude-history

  Find native Claude Code, Codex, or Grok conversations by topic, file, date, or session ID. Explain automatic indexing and provider-scoped resume. Not for codebase/git/Slack history.

• debugging-master

  Hypothesis-driven runtime debugging with temporary, auto-cleanable instrumentation across Node/TS, PHP, and browser (via HTTP). Triggers on "debug this", "add temporary logs", "instrument X", "why is this slow/wrong at runtime", "test my theory", comparing failing vs passing runs, intermittent or cr

• fable-replace

  Verified, transactional find/replace for code and docs. Use INSTEAD of sed, perl, python s.replace() or repeated Edit calls whenever a change spans more than one file or more than one spot: a rename across 50 files, a comment sweep, several dependent edits in one file that must all land or none, an

• gt:git

  Git branch mechanics with proof, not habit. Is this branch or worktree ALREADY merged (squash, rebase and recompose all fool git's own checks); rebase one branch or a whole fleet onto a moved base; rebase a branch whose work already landed upstream in another form (the oracle merge); cascade a paren

• gt:github

  Read or search GitHub (issues, PRs, review threads, comments, code, notifications) and analyze GitHub Actions (workflow runs, billing, costs, failures, rerun/cancel). Use on any GitHub URL or repo lookup. Not for implementing code fixes or PR feedback — use gt:github-pr.

• handoff-to

  Offload work to another model or agent, and pick which one (Codex/GPT-6 Astra, Sol and Luna, grok, sonnet, opus, fable). Triggers on "give this to codex", "let codex implement this", "run codex on this", "codex subagent", "tools codex", "give this to grok", "run grok on this", "offload this", "hand

• gt:improve-agents-md

  Empirically evaluate and trim ANY agent-instruction file — user/project CLAUDE.md, CLAUDE.local.md, AND AGENTS.md (the cross-tool standard read by Codex, Cursor, Gemini CLI) — to find rules a clean model already knows, rules the repo/hooks already enforce, and internal duplication, then propose evid

• gt:jev-grep

  Find the source code for a behavior when you do not know the symbol or the file, for example "where is authentication checked before a request reaches a handler?" or "which tests cover retry on timeout?". Runs `tools jev grep`, which walks the tree, asks Jev which directories, files and declarations

• gt:json2md

  For generating markdowns efficiently from json data, use this gt:json2md skill

• gt:living-docs

  Self-maintaining docs system. Bootstraps, validates, and refines minimal codebase documentation. Use for creating, updating, or auditing project docs.

• macos-control

  Use when inspecting or operating macOS apps, browser tabs, menus, forms, dialogs or multiple displays; demonstrating native Jev control; debugging stale AX trees, focus, cursor feedback or URL replacement; or recording and reviewing short screen transitions.

• gt:markdown

  Markdown notes that stay true to the code. Use when a note, report or vault page should show real code, a JSON value, a diff or a command's output instead of a hand-pasted copy; when the user says "transclude", "embed the lines", "{{lines …}}", "keep this excerpt current", "turn these file:// links

• mcp-scripting

  Call MCP tools from a plain TypeScript script via `tools scripts`, with typed bindings generated from each server's live tools/list. Use this WHENEVER a task means calling the same MCP tool many times, chaining several tools in a fixed order, looping or diffing over tool results, or when the tool yo

• meetings

  Polish a recorded meeting (Wispr Flow, Spellar, Teams) into one trustworthy file - fix misheard terms and code identifiers, re-attribute wrong speaker labels with scored rules, check the source's own summary against the transcript, and log every change as a diff. Use for "polish the transcript", "fi

• node-repl

  Drive GenesisTools from a persistent JavaScript REPL (tools node-repl, its MCP server and toolsets such as computer, movies, recorder, meetings, browser) and keep scripts that worked as named presets with parameters that run again with other values. Use for "run this in the node repl", "which toolse

• gt:plan-it

  Write comprehensive implementation plans (subsumes writing-plans - bite-sized TDD tasks, exact paths, complete code) hardened with an executor-proof contract - all judgment spent at plan time, REASON/VERIFY/ON-FAIL per task, no-improvisation covenant - so even the weakest model executes to strong-mo

• question

  Answer a question and preserve the Q→A for later review. Use when the user runs `/question <x>` (answer it, then save), or right after you give a substantive answer worth keeping to a question interjected mid-session ("why X over Y", "how does Y work", decisions, rationale, tradeoffs). Not for routi

• gt:react-compiler-debug

  Inspect React Compiler (babel-plugin-react-compiler) output. Use for "compiler output", "see compiled", "why isn't this memoized", or comparing original vs compiled components.

• recorder

  Record the screen as a movie and edit it with GenesisTools (tools recorder, the REPL's movies toolset, the recorder window), above all agent demo mode, where one call records a script of steps, marks each step, cuts the waiting and captions every step into a finished demo. Use for "record a demo", "

• gt:research

  Use when user says "research X", "look up X online", "what's the current state of X", "what are people saying about X", "find examples of X on github", "compare options for X", "is X worth using", "what do people complain about with X", or otherwise asks for information from outside the local codeba

• gt:review-proposal

  Review a GitHub PR or GitLab MR and push the result into the GenesisTools.app review window as a proposal (verdict, draft comments anchored to lines, and the agent's analysis stuck to each draft). Use when asked to "review PR/MR N", "give a review", "draft review comments", "push the review to the h

• stash

  Save/apply/unapply named code overlays across projects with `tools stash`. Use when the user wants to capture a chunk of working-tree changes for re-use, apply a previously saved stash into the current project, shape an applied stash by editing source then capturing the result (update), surgically r

• gt:summarize

  Summarize a Claude Code session — extract learnings, generate postmortem/changelog, write onboarding docs, or document what was done. Use for "summarize this session", "extract learnings", "postmortem", "write up what we did". Not for general text summarization.

• task

  Run interactive CLI commands (Metro, Vite, dev servers) with PTY capture and agent-friendly log tail. Use when the user wants to run a long-lived process with log capture, grep session logs, follow live output, or inspect session state.

• tdd

  Test-first workflow for implementing ANY feature or bugfix — use BEFORE writing implementation code, even when the user never mentions tests. Also use whenever the user says "tdd", "red-green", "test-first", "write a failing test", "reproduce this bug with a test", "regression test", pastes an error

• gt:timely

  Create Timely time-log entries from auto-tracked memories. Use when the user says "log my Timely day", "convert memories to events", "fill Timely from yesterday", "create timely entry from memory", "split my day into projects", or "categorize my Timely time". Drives a non-interactive **plan / apply*

• gt:todo

  Manage project-scoped todos with rich context capture, and put timed todos into Apple Calendar or Reminders. Use when the user wants to track tasks, schedule something at a wall-clock time, create reminders, link work items to PRs/issues, or manage work across sessions. Triggers on "add todo", "crea

• gt:typescript-error-fixer

  Fix TypeScript compile errors and eliminate `any` types. Use on failing builds, type-safety audits, or `any` cleanup.

• wrap-up

  Write the state doc that lets a fresh agent resume cold — a session wrap-up in Obsidian, or a plan-execution handoff in the repo. Triggers on 'wrap up', 'close out this session', 'summarize and hand off', 'document what we did', 'save/create the handoff', and on starting or resuming execution of a p

Slash commands (6)

• /genesis-tools:automate

  Build or run multi-step `tools` CLI automation presets.

• /genesis-tools:git-recommit

  Recompose the current branch's commits into N clean, scope-organised commits with the same final tree.

• /genesis-tools:git-recompose-branches

  Split a branch's commits into separate branches by file-pattern groups, with a verified split.

• /genesis-tools:github-pr

  Fix PR review comments — fetch, pick, implement, commit.

• /genesis-tools:setup

  Install GenesisTools so `tools` works globally.

• /genesis-tools:timelog

  Sync Timely → Azure DevOps timelogs and fill Clarity PPM timesheets.

Subagents (2)

• agent-driver

  Drives one external worker session end to end — spawn, watch, steer, resolve approvals, verify, tear down — keeping its event stream out of the orchestrator's context. One per worker session. Triggers on 'drive the codex session', 'supervise the worker', and gt:handoff-to default mode.

• explore

  Deep codebase exploration that writes a persistent report. Use instead of the built-in Explore agent when findings should be preserved — not lost when the subagent exits. Triggers on: 'explore and document', 'deep dive into', 'research how X works and save findings'.

Hooks (12)

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/track-session-files.ts

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/agents-talk-hint.ts

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/native-inbox-hint.ts

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/record-session-account.ts

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/record-session-cmux.ts

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/area-rules.ts

• SessionStart

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-lock.ts

• SessionEnd

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-lock.ts

• SessionEnd

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/record-session-cmux.ts

• UserPromptSubmit

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/record-session-cmux.ts

• PostToolUse

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/track-session-files.ts

• PostToolUse

  bun ${CLAUDE_PLUGIN_ROOT}/hooks/area-rules.ts

Similar plugins