freeze

freeze is a skill for Claude Code from bdfinst/agentic-dev-team. It costs 27 tokens per session (639 once invoked), scanned A, original, MIT.

A file-editing restriction that allows changes only to files matching a chosen pattern.

In plain words
What is it for?
Use it to lock work to a directory, file type, or other glob pattern until the restriction is removed.
Why use it?
It prevents accidental edits elsewhere in the repository while you work on a focused task.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the dev-team plugin — 98 skills, 54 agents, 4 hooks shipped together

Good fit Use it to lock work to a directory, file type, or other glob pattern until the restriction is removed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bdfinst/agentic-dev-team/freeze
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add bdfinst/agentic-dev-team --skill freeze
Clone the repo
git clone --depth 1 https://github.com/bdfinst/agentic-dev-team

Made for: Claude Code.

Or install dev-team, the plugin that ships this one along with the rest of its 98 skills, 54 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for freeze

README.md
[![agentmods](https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/freeze/github.svg)](https://agentmods.dev/skills/bdfinst/agentic-dev-team/freeze)
Your own site
<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/freeze"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/freeze/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for freeze

Your own site · 80×15
<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/freeze"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/freeze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00639
Opus 5.5 $0.00011 $0.00256
Sonnet 5.5 $0.00005 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured 1mo ago against content hash 5384b0ac72b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

freeze scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/dev-team/skills/freeze/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Freeze

Role: worker. This command restricts Write/Edit operations to files matching a glob pattern.

You have been invoked with the /freeze command.

Worker constraints

  1. Write only the freeze-state file; do not edit source.
  2. Do not enforce the lock yourself — the pre-tool-guard hook does.
  3. Be concise. Confirm the locked scope in one line.

Parse Arguments

Arguments: $ARGUMENTS

  • Positional: <glob-pattern> (required) — glob pattern for files that ARE allowed to be edited (e.g., src/auth/**, *.test.ts)

If no pattern is provided, display usage and exit:

Usage: /freeze <glob-pattern> Example: /freeze src/auth/** — only files under src/auth/ can be edited.

Steps

1. Write freeze state

Write the following JSON to .claude/hooks/freeze-state.json (relative to the current repo root — not hooks/freeze-state.json, which would sit inside the plugin's own shared install/cache directory and scope-lock every other concurrently-running session, worktree, and project on the machine; see issue #1890):

{
  "active": true,
  "allowed_patterns": ["<glob-pattern>"],
  "frozen_at": "<ISO timestamp>"
}

2. Confirm

Display:

Scope locked to <pattern>. Only matching files can be edited. Use /unfreeze to lift the restriction.

Notes

  • The hooks/pre_tool_guard.py hook resolves this same path per invoking repo via hooks/lib/artifact_paths.py's resolve_file("hooks", "freeze-state.json") — the same .claude/-scoped convention .review-passed and other per-repo runtime state already use — and blocks Write/Edit to files that do NOT match the allowed patterns.
  • Freeze state persists across tool calls within a session, and is scoped to the repo it was activated in.
  • If a session crashes while frozen, use /unfreeze in the next session to clear stale state.
  • Multiple patterns can be provided as comma-separated: /freeze src/auth/**,src/middleware/**
  • /build can also engage this same .claude/hooks/freeze-state.json contract automatically, per slice, when a plan opts into **Scope enforcement:** freeze and declares slice-level **Files:** (issue #865) — see scripts/build_slice_scope.py and the build skill's "Slice dispatch bookkeeping" section. That path is opt-in metadata, not a manual /freeze invocation, but writes/clears the identical file this command does.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 69 lines · 27 tokens per session scan A 5384b0ac72b3

Subscribe to this mod's changes

freeze is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 639 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens