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 xuiltul/animaworks --skill workspace-managergit clone --depth 1 https://github.com/xuiltul/animaworksWrote 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/xuiltul/animaworks/workspace-manager)<a href="https://agentmods.dev/skills/xuiltul/animaworks/workspace-manager"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/workspace-manager/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/xuiltul/animaworks/workspace-manager"><img src="https://agentmods.dev/badge/skills/xuiltul/animaworks/workspace-manager.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 | $0.00040 | $0.00674 |
| Opus 5.5 | $0.00016 | $0.00270 |
| Sonnet 5.5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
workspace-manager 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 22d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Management
Skill for managing project directories (workspaces) where Animas perform work.
Concept
Anima is usually at “its own home” (~/.animaworks/animas/{name}/)). When working on a project, it goes to the “workplace” (workspace) to work.
Workspaces are registered in the organization-shared registry (the workspaces section of config.json) and referenced as alias#hash.
Aliases and Hashes
- Alias: A short name assigned by humans (e.g.,
myproject) - Hash: The first 8 hex digits of the path's SHA-256, auto-generated (e.g.,
3af4be6e) - Qualified form:
myproject#3af4be6e— zero collision risk - Tool arguments accept alias only, qualified form, hash only, or absolute path
Operations
Registration
A top-level Anima that has received explicit instruction from a human uses grant_workspace_access:
{
"alias": "finance-dashboard",
"path": "/absolute/path/to/project",
"make_default": true
}
This tool requests the root host to update the organization-shared registry and the root-owned permissions.json / status.json. Do not write configuration files directly from the Anima process.
Note: An error occurs if the directory does not exist.
Note: read_memory_file(path="config.json") reads the config.json in its own Anima directory. It is not used for registering in the organization-shared registry.
List
Use core.org.workspace.list_workspaces() to inspect the shared registry. Do not use read_memory_file(path="config.json").
Remove
Treat removal as an administrator operation. For normal work, avoid overwriting an existing alias and register a new alias instead.
Change Your Default Workspace
A top-level Anima sets make_default: true when calling grant_workspace_access.
Non-top-level Animas cannot grant themselves workspace access; ask the top-level Anima via a human instruction.
Assign to Subordinates (for Supervisors)
A top-level Anima with an explicit human instruction can grant access to a subordinate or descendant by setting target_anima:
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.
- 22d ago Changed 0ce662a16be5
- 26d ago Changed · +1 lines 47afa40375cf
- 28d ago Changed 6a549bd00fc0
- 1mo ago Changed · -1 lines a12bcc8517aa
- 1mo ago First seen · 84 lines · 40 tokens per session scan A 31f4dc34a54c
workspace-manager is a skill published in the GitHub repository xuiltul/animaworks (268 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 674 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
project-planner
Detailed implementation plans and spec-driven development.
crm-operations
Resolve and safely create/update demo CRM contacts, deals, activity notes and follow-up tasks with revision checks and an atomic audit trail. Use for business-object operations; do not clean spreadsheets, analyze business performance or send customer messages.
mupeng-collab
Multi-agent project collaboration. Track progress, coordinate tasks, share context, real-time sync across distributed agents.
mupeng-org
Manage agent organizations. Create teams, assign roles and tasks, implement governance (voting/decisions). Build the agent society.
engineering-pr
Pull request lifecycle management. Use when you need to create a PR, handle PR reviews, resolve merge conflicts, or manage the PR-to-merge workflow. Extends the engineering skill with GitHub-specific tools and decision framework.