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.
npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreezegit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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.
[](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/workspace-unfreeze)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/workspace-unfreeze"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/workspace-unfreeze/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.
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/workspace-unfreeze"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/workspace-unfreeze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00640 |
| Opus 5 | $0.00017 | $0.00320 |
| Sonnet 5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
workspace-unfreeze 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace unfreeze
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user runs /workspace-unfreeze on a frozen path |
| Authority | Human-gated: requires explicit human invocation, previews the target marker file and the deletion consequence, and asks before deleting the freeze lock marker file; otherwise reversible local: deletes only the freeze lock marker file; rollback is recreating the marker file. No remote mutation. |
| Side effect | Deletes the freeze lock marker file for the named path. The deletion is unrecoverable, but the marker is re-creatable by re-creating the <path>.freeze-lock file beside the path with content naming the target path |
| Done | The named path is editable again (no freeze lock marker present for it) |
Inputs
- Path (required): the frozen path to unfreeze.
Procedure
- Receive the path argument from the explicit /workspace-unfreeze invocation. Do not act on any model-generated or inferred path. Done when: the path argument is confirmed as human-supplied.
- Resolve the marker path from the invocation: accept an explicit marker path from the human, or derive it from the freeze convention: a marker file named
<path>.freeze-lockbeside the frozen path, whose content names the target path. Verify the resolved file exists and names the target path. If it does not, treat as Marker not found. Never glob or scan for candidate markers. Done when: the marker file path is resolved and verified, or the path is confirmed already editable. - Before deleting, preview the marker file path and state the consequence: the
<path>.freeze-lockmarker on that path will be removed and the path will become editable. Obtain explicit human confirmation. Done when: the human has seen the preview and the consequence and confirmed deletion. - After human confirmation, delete only that single marker file. Do not delete any other file, do not edit the protected path's contents, and do not touch any other freeze marker. Done when: the single marker file is deleted.
- Confirm the marker file is gone and the named path is editable again. Done when: the marker file is absent and the path is editable.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · -30 tokens per session 7f16ef21b705
- 7d ago First seen · 38 lines · 65 tokens per session scan A 053e8c672a68
workspace-unfreeze is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 640 once invoked, about $0.0002 per session on Opus 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…