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 chuancyzhang/deepseek-cowork --skill file-systemgit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote 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/chuancyzhang/deepseek-cowork/file-system)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/file-system"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/file-system/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/chuancyzhang/deepseek-cowork/file-system"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/file-system.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 | $0.00022 | $0.00719 |
| Opus 5.5 | $0.00009 | $0.00288 |
| Sonnet 5.5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
file-system 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File System Skill
This built-in skill handles workspace path operations and plain text files only.
Capabilities
- List Paths: Explore workspace files and directories.
- Read Plain Text: Strictly decode and page through
.txt,.md,.json, source code, logs, and similar text files up to 10 MiB. - Apply Text Patches: Create, update, move, or delete up to 100 plain-text files with one exact patch.
- Rename Paths: Rename or move files and directories without parsing contents.
- Delete Paths: Delete files or directories after confirmation.
Boundaries
text_file_readandapply_patchrefuse DOCX, PPTX, XLSX, XLS, and PDF paths.- To read Office/PDF documents, use the bundled
document-readercapability anddocument_read. If it was explicitly disabled, enable it in the capability store. - To create or modify Office/PDF documents, use
run_python_codewith the appropriate document library. - Path search is owned by
command-toolsthroughglobandgrep. - User confirmation is owned by
interaction; delete confirmation uses the shared interaction bridge internally. - With God Mode off, trusted reads can use paths outside the workspace. New files and edits within this run's artifact directory are allowed; changes elsewhere require an execution-layer approval for the exact operation. Use the artifact directory from the runtime context, not another run's directory. God Mode preserves existing access and delete confirmations. Write paths still reject symbolic links and directory junctions, and existing-file integrity checks always apply.
Usage Guidelines
- Prefer relative workspace paths.
- Use
globto discover paths andgrepto locate matching lines. Neither tool returns the complete ordered file or grants a write credential. - Before changing existing content, call
text_file_readwithoffset=1and nolimit. A paged read never grants write audit even when it reaches the end of the file. - Files with a recognized Unicode BOM or valid UTF-8 need no encoding argument. Other encodings must be explicit; decode failures are returned and never replaced or ignored.
- Use
apply_patchfor every plain-text creation or content change. The patch must start with*** Begin Patch, end with*** End Patch, and contain*** Add File,*** Update File,*** Delete File, optional*** Move to, and exact@@hunks. Pure EOF additions require*** End of File. - Use enough unchanged context to make each hunk unique. Matching is exact: whitespace and Unicode variants are not normalized.
- All deletes in one patch are confirmed together after preflight. Rejection or timeout leaves the entire patch unapplied.
- Multiple independent plain-text reads can be grouped through
parallel_tools. - Patches, renames, and deletes must stay as direct single-tool calls.
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.
- 1mo ago Changed 3b2af640ad52
- 1mo ago First seen · 45 lines · 22 tokens per session scan A 342a027148a6
file-system is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 719 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 2026-09-04.
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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.
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.