MCPInstall

repo-rename

Preview or rename a GitHub repo, or move a local repo to another parent directory. Preserve Codex CLI and Claude Code continuity references.

Installs
92
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/paulrberg/agent-skills --skill repo-rename
  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 repo-rename 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.

Repo Rename

If a slash or dollar invocation already added these instructions to the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool.

Preview the complete GitHub, Git, filesystem, and agent-continuity mutation set before applying a repository rename.

Scope

  • Rename the current GitHub repository, matching local folder, and origin URL.
  • With two path arguments, move the source repository to the destination without changing its name, GitHub identity, or origin. Both paths must have the same folder name. Preview missing parent directories before creating them.
  • If the repository has no Git remotes, rename only local state: the folder, continuity references, and repository content. The helper then skips the GitHub rename and the origin update. A repository with any remote still requires a valid GitHub context.
  • Only when the repository has an active Claude Code or Codex transcript, update literal old paths in ~/.claude/projects, ~/claude/projects when present, ~/.codex/sessions, and ~/.codex/config.toml. This continuity update does not apply to repos with no active transcripts.
  • Update constrained literal old-name references inside the repository, excluding VCS, dependencies (including Python virtual environments), caches, and generated build directories.
  • For a same-name move, replace only the old absolute repository path inside repository files.
  • By default, use tracked repository files and skip PROMPT.md, TODO.md, and symlinks before reading replacement candidates. Prune excluded directories during discovery. When the user explicitly authorizes updating notes, dependencies, caches, or generated files, pass --include-local-state to both preview and apply. This includes those repository text files while preserving file permissions. Symlinks, binary files, and .git remain excluded.
  • The helper honors CLAUDE_CONFIG_DIR and CODEX_HOME, gates continuity updates on active transcripts, and replaces only the absolute repository path in continuity stores and Codex config.
  • Do not modify other transcript stores, archives, remotes, or repositories.

Workflow

  1. Resolve the source repository from the first of two path arguments, or from the current directory for a rename. Check whether it has any active AI chat transcript before treating continuity preservation as in scope:

    • Claude Code: resolve ${CLAUDE_CONFIG_DIR:-~/.claude}/projects/<encoded-repo-path> (the absolute repo path with every non-alphanumeric character replaced by -) and check it exists and is non-empty.
    • Codex: resolve ${CODEX_HOME:-~/.codex}/sessions and check whether any session file references the exact absolute repo path.
    • If neither exists, state that the transcript-continuity update does not apply. In that case, the rename may still proceed for the GitHub, git, filesystem, and repository-content changes below.
  2. Resolve the skill directory and run the helper from the repository to produce a read-only preview:

    uv run <skill-dir>/scripts/repo-rename.py <new-name> --dry-run
    

    For a same-name move, run from any directory:

    uv run <skill-dir>/scripts/repo-rename.py <source-path> <destination-path> --dry-run
    

    The helper requires a clean worktree, matching GitHub repo/folder names, a free target path, and valid GitHub context. For a repository with no remotes, it requires only a clean worktree and a free target path. It reports "local_only": true and a local:<old>-><new> confirmation token. It prints the old/new repo and paths, exact confirmation token, external commands, directory moves, every replacement file, occurrence counts, and rollback coverage. Same-name moves use move:<absolute-source>-><absolute-destination> tokens. Linked worktrees and external Git directories are unsupported.

  3. If --dry-run was requested, return the preview and stop. A successful dry run must not change the GitHub repo, remote, folder, config, transcripts, or repository files.

  4. Otherwise present the complete preview and require explicit confirmation in a subsequent user message. Explain that the confirmation authorizes the GitHub rename, local folder move, Claude project-folder move when enabled, origin update, and every listed continuity/repository replacement. For a local-only preview, state that no GitHub or origin change occurs. Lead with ### ⚠️ Rename preview — no changes made. Show GitHub, folder, origin, replacement counts, and rollback coverage in compact tables, then the exhaustive file/count list. Put the exact confirmation token alone in code formatting. If any preview fact changes, regenerate it and ask again.

    For same-name moves, show the unchanged GitHub identity and origin, plus each parent directory to create.

  5. After confirmation, pass the preview's exact token:

    uv run <skill-dir>/scripts/repo-rename.py <new-name> --apply --confirm '<owner/old->owner/new>'
    

    For a same-name move, pass both paths and the preview's move: token instead.

    The helper re-runs preflight, backs up every replacement file, applies deterministic literal replacements, and attempts rollback on failure. Never bypass its clean-tree, target-path, or confirmation checks.

  6. Verify the helper's result with gh repo view, git remote get-url origin, pwd -P, and a search for remaining old absolute-path/name references in the listed scope. Report intentional remaining matches separately.

Completion

Dry-run completion is a full mutation preview with zero writes. Apply completion requires the new GitHub identity, folder, remote, and listed continuity references to agree, plus a clean verification report. If rollback is incomplete, stop and lead with ### ⛔ Rollback incomplete, then report every failed rollback action before doing anything else. On success, use ### ✅ Repository renamed and a surface/expected/verified table. Keep helper JSON, confirmation tokens, commands, paths, URLs, and rollback errors exact and undecorated.

FAQ

What does the repo-rename skill do?

Preview or rename a GitHub repo, or move a local repo to another parent directory. Preserve Codex CLI and Claude Code continuity references.

How do I install repo-rename?

Run npx skills add https://github.com/paulrberg/agent-skills --skill repo-rename 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/repo-rename/ (personal) or .claude/skills/repo-rename/ (project).

Which AI agents can use repo-rename?

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 repo-rename 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 repo-rename?

It is published by paulrberg in paulrberg/agent-skills. It has 92 recorded installs.

More from paulrberg/agent-skills

View all →

effect-ts

paulrberg/agent-skills

Use for nontrivial Effect 4 work including services/layers, typed errors, Schema/JsonSchema, Config, runtime/concurrency, @effect/vitest, effect/ai and @effect/ai-, effect/sql and @effect/sql-, Effect Atom (@effect/atom-), or @prb/effect-next.

Data & Databases3.1K installs

tailwind-css

paulrberg/agent-skills

Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.

cli-gh

paulrberg/agent-skills

Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions.

code-polish

paulrberg/agent-skills

Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope.

AI & Agents2.8K installs

yeet

paulrberg/agent-skills

Use for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet.

AI & Agents2.6K installs

bump-release

paulrberg/agent-skills

Cut a release: bump versions, write changelogs, commit, tag.

AI & Agents2.4K installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs