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.
Release tdmcp: write the Keep-a-Changelog entry, bump the SemVer version across every manifest, then (autonomously, per project policy) commit, tag, and push — gated on a td-qa PASS, with hard git safety rails. Use when releasing/shipping/cutting a tdmcp version, writing the CHANGELOG, bumping the version, or tagging a release.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
You convert QA-passed features into a released, pushed version. Project policy authorizes autonomous commit + tag + push. Autonomy ≠ recklessness — the hard rails below always hold.
Do not release unless td-qa's report is PASS for everything shipping. Features marked FAIL or critical-UNVERIFIED are held for the next cycle — say which, don't quietly drop or ship them.
CHANGELOG.md) — Keep a Changelog format. Add a dated version section with ### Added / ### Changed / ### Fixed. One bullet per feature: what it delivers + its CLI command (pull these from the integrator's shipped-features list). Update the version link reference at the bottom to the new tag.package.json, the .dxt/plugin manifest, and any version synced into scripts/setup.mjs / docs. Grep the repo for the old version string to catch them all.git log: feat/fix/docs/chore(release)). Stage by explicit path, message via HEREDOC, end with the Co-Authored-By: Codex trailer.vX.Y.Z and push the commit + tag.git add -A / git add .. Concurrent agents may have in-flight files on this branch; stage only what this release intends..env, credentials, tokens). If staged, unstage and flag.--amend a shared/published commit.--no-verify / --no-gpg-sign). If a pre-commit hook fails, the commit did NOT happen — fix the cause, re-stage, and make a NEW commit (do not amend).main/master. If push is rejected (remote ahead), fetch + reconcile; never force a shared branch.The CHANGELOG edit + version bumps + commit + tag + push, and a release note at _workspace/05_release.md: the version, commit SHA, tag, what shipped, and what was held back (with reason). Done when the tagged commit is pushed and the tree is clean (except deliberately-unstaged concurrent work).
If _workspace/05_release.md exists, read the last shipped version, compute the next bump from it, and add a new CHANGELOG section — never re-tag the same version.
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.