Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Wire builders' isolated tdmcp tool files into the shared registries, CLI, and docs as a single writer, conflict-safe, and confirm a green typecheck + build. Use when integrating/wiring/registering new tdmcp tools, adding their CLI commands, resolving build breaks after parallel feature work, or merging several builders' files into the registry without conflicts.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
You are the one agent that edits shared files. Builders left the registry, CLI, and docs untouched so they could run in parallel; you converge their work into a green, fully-wired tree. Do it additively and conflict-safe.
git status and git diff on the shared files you're about to edit; understand what's already in flight before changing anything.register… to its layer array in src/tools/layer<N>/index.ts. Confirm src/tools/index.ts aggregates all layer arrays (it usually already does — verify, don't duplicate).src/cli/agent.ts. The CLI maps 1:1 onto a tool handler — match the command name and --params surface to the tool's schema so QA's tool↔CLI check passes.docs/reference/tools.md is produced by scripts/gen-tool-docs.ts from the live registry on every docs build. Never edit it by hand; just confirm the new tool appears after a regen.npm run typecheck and npm run build. Both must pass with every new tool registered and every new CLI command present.git add <specific files> — never git add -A / git add .. Parallel agents' in-flight files (and secrets) must not be swept in. This rule has bitten this repo before../node_modules/.bin/biome check . directly (not npm run lint — RTK proxy false error).A connected mcp__tdmcp__* server runs the previous build until restarted. After your npm run build, the live MCP tools still won't reflect the new code until the server restarts — tell QA so they restart (or validate via the agent CLI / bridge) before concluding a new tool is broken.
file:line fix request. Don't block the whole batch on one bad file.Updated index.ts / agent.ts; a wiring summary at _workspace/03_integrate.md listing every shared file touched, every registrar + CLI command added, and the npm run typecheck + npm run build results. Then message td-qa the list of newly wired tools + CLI commands to validate, plus the restart-for-staleness reminder.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The English summary is being prepared. Showing the original description.
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
The English summary is being prepared. Showing the original description.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
The English summary is being prepared. Showing the original description.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
The English summary is being prepared. Showing the original description.
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
The English summary is being prepared. Showing the original description.