MCPInstall

t3-code-continue-thread

Continue work from an earlier T3 Code thread by resolving its UUID, identifying the correct checkout or worktree, and producing a handoff for the normal agent.

Installs
155
Last 24h
+9
Trending rank
#9128
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/onmax/nuxt-skills --skill t3-code-continue-thread
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads t3-code-continue-thread automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Use this skill when work must move from one T3 Code thread into a fresh thread. The input is the source thread UUID (for example a40b36e9-04d9-4a70-9f99-4ecfda1eef4b) and optionally the new focus.

  1. Resolve the source thread with the bundled script:

    python3 <skill-dir>/scripts/find_thread.py <uuid> --full
    

    The script reads T3 Code's local databases under ${CODEX_HOME:-$HOME/.codex} and returns JSON containing the thread record, source cwd, branch, commit, origin, conversation, and a recommended_worktree. Treat the reported cwd/worktree as the checkout to inspect first. Compare recommended_worktree.matches_recorded with the thread's recorded branch and commit. If it is false, the path has been reused or changed: use matching_worktrees when present, otherwise locate or create the checkout for the recorded branch/commit only after the normal agent verifies it. If the path is missing, use the recorded branch and commit to locate an existing git worktree; do not silently switch to an unrelated checkout. A non-zero exit or found: false means the UUID could not be resolved.

  2. Delegate continuation context preparation to a subagent when collaboration is available. Give it the script output and the requested focus, and ask it to use the handoff skill to write a compact continuation handoff. The subagent should preserve the source thread's exact repository, branch, worktree, dirty-file ownership, decisions, proof, blockers, and next action. It must not mutate the source checkout merely to prepare the handoff.

  3. The subagent's handoff path is the $handoff consumed by the normal agent. Report the absolute path explicitly. The normal agent must read that file before acting and then continue from its stated worktree and branch. If delegation is unavailable, create the handoff yourself using the handoff skill and return its absolute path.

Do not claim the continuation is complete merely because the source thread was found. The continuation is ready only when the handoff exists and names the checkout/worktree and the next concrete action. Never include credentials or private configuration values from the thread transcript in the handoff.

FAQ

What does the t3-code-continue-thread skill do?

Continue work from an earlier T3 Code thread by resolving its UUID, identifying the correct checkout or worktree, and producing a handoff for the normal agent.

How do I install t3-code-continue-thread?

Run npx skills add https://github.com/onmax/nuxt-skills --skill t3-code-continue-thread in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/t3-code-continue-thread/ (personal) or .claude/skills/t3-code-continue-thread/ (project).

Which AI agents can use t3-code-continue-thread?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is t3-code-continue-thread safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains t3-code-continue-thread?

It is published by onmax in onmax/nuxt-skills. It has 155 recorded installs.

More from onmax/nuxt-skills

View all →

nuxt

onmax/nuxt-skills

Nuxt full-stack Vue framework with SSR, auto-imports, and file-based routing. Use when working with Nuxt apps, server routes, useFetch, middleware, or hybrid rendering.

Frontend & Design8.6K installs

vue

onmax/nuxt-skills

Vue 3 Composition API, script setup macros, reactivity system, and built-in components. Use when writing Vue SFCs, defineProps/defineEmits/defineModel, watchers, or using Transition/Teleport/Suspense/KeepAlive.

reka-ui

onmax/nuxt-skills

Use when building with Reka UI (headless Vue components) - provides component API, accessibility patterns, composition (asChild), controlled/uncontrolled state, virtualization, and styling integration. Formerly Radix Vue.

Frontend & Design7.4K installs

nuxt-ui

onmax/nuxt-skills

Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming. Use when creating interfaces, customizing themes to match a brand, building forms, or composing layouts like dashboards, docs sites, and chat interfaces.

vitest

onmax/nuxt-skills

Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

Testing & QA3.1K installs

nuxt-seo

onmax/nuxt-skills

Nuxt SEO meta-module with robots, sitemap, og-image, schema-org. Use when configuring SEO, generating sitemaps, creating OG images, or adding structured data.

Marketing & SEO3.1K installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.