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 bammt/XuanShu-Agent --skill xuanshu-workspace-executiongit clone --depth 1 https://github.com/bammt/XuanShu-AgentWrote 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/bammt/xuanshu-agent/xuanshu-workspace-execution)<a href="https://agentmods.dev/skills/bammt/xuanshu-agent/xuanshu-workspace-execution"><img src="https://agentmods.dev/badge/skills/bammt/xuanshu-agent/xuanshu-workspace-execution/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/bammt/xuanshu-agent/xuanshu-workspace-execution"><img src="https://agentmods.dev/badge/skills/bammt/xuanshu-agent/xuanshu-workspace-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.00477 |
| Opus 5.5 | $0.00012 | $0.00191 |
| Sonnet 5.5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
xuanshu-workspace-execution 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 2mo 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.
What it actually says
Application workspace execution
The application has a persistent isolated workspace exposed as
$XUANSHU_WORKSPACE. User uploads and all deliverable files belong there.
Complete bound Skill packages are copied into $XUANSHU_SKILLS_DIR. The
package roots selected for the current Agent are listed in
$XUANSHU_SKILL_ROOTS. Do not import a top-level scripts or references
package: several bound Skills can contain directories with those same names.
$XUANSHU_SKILL_MAP is a JSON object mapping each selected Skill's unique
Python namespace to its complete package root.
Import code through the unique namespace, for example:
from xuanshu_skills.skill_3_official_doc_writer import SKILL_ROOT
from xuanshu_skills.skill_3_official_doc_writer.scripts.generator import build
rules = (SKILL_ROOT / "references" / "format.md").read_text(encoding="utf-8")
Read the actual namespace names from $XUANSHU_SKILL_MAP; never guess them.
Each namespace exposes SKILL_ROOT, so references/, assets/, templates,
and other non-Python resources remain tied to the correct Skill without any
extra copy. Relative paths in a Skill are resolved from that SKILL_ROOT.
Use execute_skill_script when starting an existing script from its package
directory is convenient. It is an optional helper: execute_python and
execute_command may also write new code, call Skill modules, install
dependencies, configure fonts, or combine several resources when the task
requires it. Dependencies are installed into the application's private
$PIP_TARGET under $XUANSHU_RUNTIME_DIR, which is injected consistently on
every execution.
Before finishing, check the tool result and report only the user-facing result.
The platform publishes files from $XUANSHU_WORKSPACE separately, so never
print host filesystem paths or construct Markdown links to local files.
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.
- 2mo ago First seen · 46 lines · 30 tokens per session scan A 4e221ee8b77a
xuanshu-workspace-execution is a skill published in the GitHub repository bammt/XuanShu-Agent (2 stars, last pushed 26d ago), licensed Apache-2.0. It adds 30 tokens to every session and 477 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 2026-08-31.
Other skills, from other repositories
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
agent-harness-testing
A testing method for coding tasks in unfamiliar projects. It first discovers how the project is tested, then uses a failing check followed by a passing check to verify a change.
visual-acceptance
A visual final-review method for user-interface changes. It checks the rendered result with repeatable screenshots, pixel values, computed styles, and CSS layering checks across themes.
design-prototype
Frontend UI prototype workflow — clarify intent, explore directions, preview across viewports, diff against references, deliver with screenshot evidence.
office-docx
A tool for creating and reading editable Microsoft Word documents in the .docx format. It supports common document parts such as headings, paragraphs, tables, code blocks, lists, and centred titles.
deepseek-harness
Use when running, scripting, or extending DeepSeek Harness (dsh) 0.2.1 — npx @deepseek-ai/dsh web / dsh --profile, headless one-shot runs, the deepseek-harness-sdk Python DeepSeekHarness client, or Cordis plugins that export apply(ctx) and register tools with defineTool; also when a profile patch fails to load, tools…