agentleFS
timurgaleevtimurgaleev/vibestack/skills/freeze/SKILL.md

freeze

Skill8 starsChanged 6 months agoMITView on GitHub

Restrict file edits to one directory until /unfreeze; blocks edits outside the allowed path.

47 other projects use a version of this, 24 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ios-clean, ios-fix and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 9 projects that use this

  • ShreyRaviSkill

    setup-gbrain

    Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)

    Also in 6 projects that use this

  • ShreyRaviSkill

    sync-gbrain

    Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state probing, native code-surface registration, capability checks, and a verdict block. Re-runnable, idempotent. Use when: "sync gbrain", "refresh gbrain", "re-index this repo", "gbrain search isn't finding things". (gstack)

    Also in 6 projects that use this

  • +1 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

4 rules. 1 is common, 1 is distinctive, and 2 are very specific to this project.

  • 1

    Common

    Most of the 38 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If this session was compacted, the copy of this skill in context may be cut off.

    line 33
  2. Very specific:

    Read ${CLAUDE_SKILL_DIR}/SKILL.md from disk and resume at the step you are on.

    line 34
  3. Distinctive:

    Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module.

    line 38
  4. Common:

    Ask the user which directory to restrict edits to:

    line 61

“Common” is measured: kept by at least 6 in 10 of the 38 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

If this session was compacted, the copy of this skill in context may be cut off. Read ${CLAUDE_SKILL_DIR}/SKILL.md from disk and resume at the step you are on.

When to invoke

Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits".

/freeze — Restrict Edits to a Directory

Lock file edits to a specific directory. Any Edit, Write or NotebookEdit operation targeting a file outside the allowed path will be blocked (not just warned).

Where this is enforced. The block is a Claude Code PreToolUse hook. Cursor, Kiro and Codex install the same skill, but the hook is not guaranteed to run there; outside Claude Code /freeze is instruction-only. On those hosts, tell the user the boundary is advisory: you will keep your own edits inside it, but nothing blocks an edit that lands outside.

Copilot CLI is the exception. When the configuration payload is installed (./install --with-config or --only=config), the user hook file ~/.copilot/hooks/vibestack.json (under $COPILOT_HOME when set) runs the same check on every edit, and it blocks only while a freeze directory is set: after /unfreeze, or before /freeze is ever run, every edit goes through. Without the configuration payload it is instruction-only there as well.

Setup

Ask the user which directory to restrict edits to:

"Which directory should I restrict edits to? Files outside this path will be blocked from editing."

Once the user provides a path, set it with the shared state writer. It resolves the physical absolute path, refuses a path that does not exist or resolves to /, and writes the state file atomically:

bash "${CLAUDE_SKILL_DIR:-$HOME/.claude/skills/freeze}/bin/freeze-state.sh" set "<user-provided-path>"

Report success only if the command exits 0 and prints FREEZE_DIR=. On FREEZE_ERROR (a mistyped or missing path, or /), tell the user no boundary was set and ask for the path again. On FREEZE_BUSY, another writer holds the lock — retry once it finishes, and never write or delete the state file directly.

Tell the user: "Edits are now restricted to <FREEZE_DIR>/. Any Edit, Write or NotebookEdit outside this directory will be blocked. To change the boundary, run /freeze again. To remove it, run /unfreeze."

How it works

The hook parses file_path out of each Edit/Write payload (notebook_path for NotebookEdit), resolves the path fully — including a final component that is itself a symlink — and checks whether it starts with the frozen directory. If not, it returns a hookSpecificOutput envelope carrying permissionDecision: "deny". The nesting matters: Claude Code ignores a top-level permissionDecision, so a deny emitted at the top level lets the edit through.

Freeze is the deny tier, so it fails closed: a payload it cannot parse, a payload with no path, a relative saved boundary, and any unexpected hook error are all blocked, not allowed. Its ask-tier sibling /careful makes the opposite call on the same input. Both share one extractor (careful/bin/hook-extract.sh).

The boundary lives in ~/.vibestack/freeze-dir.txt, not in the session. Ending or killing a conversation stops its hooks but leaves the file in place, so the next session that loads the freeze hook (/freeze, /guard, /investigate) enforces the same boundary again. Only /unfreeze removes it.

Notes

  • The trailing / prevents /src from matching /src-old
  • Applies to Edit, Write and NotebookEdit only — Read, Bash, Glob, Grep are unaffected
  • Bash commands like sed -i can still modify files outside the boundary
  • A symlink inside the boundary pointing outside it is resolved and blocked
  • A path is allowed only when both readings of it are inside: the physical one (<dir-symlink>/.. is the parent of the link's target) and the textual one (.. folded as text)
  • A tool path that is ~ or starts with ~/ is expanded to $HOME (~user/... is not). A Windows drive-letter (C:\..., C:/...), UNC (\\server\share) or any other path containing a backslash (..\out) is denied outright: the hook runs under bash and cannot place it against the boundary
  • A path containing a newline or carriage return, or longer than 4096 characters, is denied
  • A path with spaces in it works — only leading and trailing whitespace is trimmed from the saved boundary, and a leading ~ is expanded
  • To deactivate: run /unfreeze — ending the conversation does not remove the boundary

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.