Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
How to migrate the tdmcp Codex Desktop bundle from legacy .dxt to .mcpb (MCP Bundle) and keep it building — covers the manifest schema (verify against the installed packer, never hardcode), the build-dxt.mjs packer/zip-fallback flow, the npm scripts, and the full .dxt→.mcpb reference sweep across docs and scripts. Use when packaging or migrating the tdmcp desktop bundle.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Anthropic renamed Desktop Extensions from DXT (.dxt, packer
@anthropic-ai/dxt, manifest key dxt_version) to MCPB (.mcpb, packer
@anthropic-ai/mcpb, manifest key manifest_version). Legacy .dxt still
installs in Codex Desktop, but new directory submissions should ship .mcpb.
scripts/build-dxt.mjs is already MCPB-aware: it tries @anthropic-ai/mcpb
first, falls back to legacy @anthropic-ai/dxt, then to a system zip. The
bundle stages manifest.json at the archive root + dist/, recipes/, td/,
README.md, LICENSE, package.json, and a production-only node_modules. So
the migration is mostly renaming the output + the references, not a rewrite.
dxt/manifest.json currently declares "manifest_version": "0.3" — already the
modern MCPB key (not the legacy dxt_version), so the manifest is largely correct.
manifest_version, check
what the installed packer accepts:
npx --yes @anthropic-ai/mcpb --help (look for pack / validate). If it
ships a validate command, run it against dxt/manifest.json and let it tell
you. Only change manifest_version if validation demands it. A wrong value
breaks install — this is why we verify rather than assume a number.tdmcp.mcpb. In scripts/build-dxt.mjs: change
outFile to tdmcp.mcpb and update the log lines (they say .dxt). Keep the
packer-preference order and the zip fallback intact — both must still work.
Optionally rename the script file to build-mcpb.mjs (update the npm script if
you do).package.json): rename build:dxt → build:mcpb pointing at
the script. Only keep a build:dxt alias if something external depends on the
old name (grep first); otherwise replace it cleanly — no compatibility cruft.
Check the version script too (it stages dxt/manifest.json)..dxt → .mcpb in:
docs/guide/{install,troubleshooting,glossary}.md + their docs/pt/ mirrors,
docs/DEPLOYMENT.md, docs/reference/cli.md, scripts/setup.mjs,
README.md. Also grep .github/ for any release workflow that builds or
uploads tdmcp.dxt / runs build:dxt.releases/latest/download/tdmcp.dxt point at a published asset. After this
change the next release ships tdmcp.mcpb; update those links to .mcpb
and record that a new release must be cut so the asset exists (the current
v0.3.0 asset is still .dxt). Note this for the human in migration notes.Where docs explain "one-click Desktop Extension", keep the explanation and add
that .dxt still installs (legacy) while .mcpb is current. Don't delete info
that helps users who already downloaded the .dxt.
npm run build # populate dist/
npm run build:mcpb # (renamed) → must emit tdmcp.mcpb
unzip -l tdmcp.mcpb # manifest.json at root + dist/ present
The dxt/ directory name and dxt/manifest.json path can stay as-is (internal
paths the script references) — renaming the directory is optional churn and not
required for a valid .mcpb. If you rename it, update build-dxt.mjs,
package.json's version script, and sync-manifest-version.mjs.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。