shell-agent-file-workflow

shell-agent-file-workflow is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 23 tokens per session (730 once invoked), scanned A, original, MIT.

A workflow for delegating file generation to an autonomous shell agent when direct file tools fail.

In plain words
What is it for?
Use it for complex file creation that needs several steps, libraries, or automatic recovery.
Why use it?
The agent can choose an implementation, run it, inspect the result, retry errors, and help locate generated files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # Output might show: ./workspace/nested/path/presentation.pptx.

Good fit Use it for complex file creation that needs several steps, libraries, or automatic recovery.

Compare 6 skills from other repositories ↓
About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

HKUDS/OpenSpace · 7,544 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace
agentmods
npx agentmods add skills/hkuds/openspace/shell-agent-file-workflow

Made for: Claude Code, Codex.

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 shell-agent-file-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/shell-agent-file-workflow/github.svg)](https://agentmods.dev/skills/hkuds/openspace/shell-agent-file-workflow)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/shell-agent-file-workflow"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/shell-agent-file-workflow/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 shell-agent-file-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/hkuds/openspace/shell-agent-file-workflow"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/shell-agent-file-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 730 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 $0.00023 $0.00730
Opus 5 $0.00012 $0.00365
Sonnet 5 $0.00005 $0.00146
Haiku 4.5 $0.00002 $0.00073

Measured 5d ago against content hash de38b5ec4274, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

shell-agent-file-workflow 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.

benchmarks/gdpval/skills/shell-agent-file-workflow/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Agent File Generation Workflow

When direct document or file generation approaches fail, delegate the task to shell_agent which can autonomously write code, execute it, and retry on errors. Generated files may appear in nested workspace directories.

When to Use

  • Direct file generation tools or create_file functions fail for complex formats
  • Complex file creation requiring multiple steps, libraries, or error recovery
  • When you need an autonomous agent to figure out how to accomplish a goal
  • File generation that requires iteration and automatic error fixing

Workflow Steps

Step 1: Delegate File Generation to shell_agent

Use shell_agent with a clear, specific task description:

shell_agent(task="Create a [file type] with [specific content/structure requirements]")

The agent will:

  • Decide whether to use Python or Bash
  • Write and execute code
  • Inspect output and iterate
  • Automatically retry and fix errors (up to several rounds)

Step 2: Locate Generated Files

Files may be created in nested directories within the workspace. Use find to locate them:

find . -name "*.extension" -type f

For multiple file types:

find . -type f \( -name "*.pptx" -o -name "*.docx" -o -name "*.pdf" \)

For recently modified files (last 10 minutes):

find . -name "*.extension" -type f -mmin -10

Step 3: Copy Files to Working Directory

Once located, copy the file to your working directory:

cp /path/to/found/file.extension ./

Example

Creating a PowerPoint Presentation

# Step 1: Delegate to shell_agent
shell_agent(task="Create a 10-slide PowerPoint presentation covering: topic A, topic B, topic C")

# Step 2: Find the generated file
find . -name "*.pptx" -type f

# Output might show: ./workspace/nested/path/presentation.pptx

# Step 3: Copy to working directory
cp ./workspace/nested/path/presentation.pptx ./

Creating a PDF Report

# Step 1: Delegate generation
shell_agent(task="Generate a PDF report with charts and tables from the provided data")

# Step 2: Locate output
find . -name "*.pdf" -type f -mmin -5

# Step 3: Retrieve file
cp ./generated/reports/output.pdf ./

Read the full file on GitHub · 103 lines

Files

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.

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. 5d ago First seen · 103 lines · 23 tokens per session scan A de38b5ec4274

Subscribe to this mod's changes

shell-agent-file-workflow is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 27d ago), licensed MIT. It adds 23 tokens to every session and 730 once invoked, about $0.0001 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 2026-09-03.

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

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

feishu

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

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

overleaf-sync

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens