workspace

workspace is a skill for Claude Code, Codex from aws-samples/sample-strands-agent-with-agentcore. It costs 41 tokens per session (672 once invoked), scanned A, original, MIT.

A workspace file service for reading and writing files shared during a session. It can access uploaded files and files created by the coding agent or other tools.

In plain words
What is it for?
Use it to list session files, read uploaded data or generated documents and images, and save files under the supported workspace folders.
Why use it?
It gives different tools a common place to exchange files without copying them between separate environments.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aws-samples/sample-strands-agent-with-agentcore/workspace
Any agent
npx skills add aws-samples/sample-strands-agent-with-agentcore --skill workspace
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-strands-agent-with-agentcore

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 workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/workspace.svg)](https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/workspace)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-strands-agent-with-agentcore/workspace"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-strands-agent-with-agentcore/workspace.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.00672
Opus 5 $0.00020 $0.00336
Sonnet 5 $0.00008 $0.00134
Haiku 4.5 $0.00004 $0.00067

Measured 4d ago against content hash 791784d56ac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workspace 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 4d 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.

chatbot-app/agentcore/skills/workspace/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace

Provides unified read/write access to all files in the current session. The userId and sessionId are injected automatically — you only specify the logical path.

Path Conventions

Prefix What it accesses
uploads/<file> Files uploaded by the user
code-agent/<file> Files created by the code agent (auto-synced)
code-interpreter/<file> Files created in the Code Interpreter workspace
documents/powerpoint/<file> PowerPoint presentations
documents/word/<file> Word documents
documents/excel/<file> Excel spreadsheets
documents/image/<file> Images from other tools

Note: Files written under /mnt/workspace persist for the chat session, and user uploads are available under /mnt/workspace/inputs. Code Agent downloads session uploads into its own working directory when delegated.

Usage

See everything in the session:

workspace_list()
workspace_list("uploads/")
workspace_list("code-agent/")

Read a file the code agent created:

workspace_read("uploads/data.jsonl")           # uploaded structured data
workspace_read("code-agent/calculator.png")   # binary → base64
workspace_read("code-agent/report.md")        # text → string

Pass a file from one skill to another:

result = workspace_read("documents/excel/data.xlsx")   # encoding: base64
workspace_write("code-agent/data.xlsx", result["content"], encoding="base64")

Notes

  • Text files return encoding: "text" with plain string content. Large text reads are bounded; when truncated is true, use Code Interpreter for the complete file instead of repeatedly reading it into model context. Code Interpreter uses /mnt/workspace/inputs/<file>.
  • JSON, JSONL, and NDJSON uploads are text files; large chat attachments may be truncated in model context, but the complete file remains under uploads/
  • Binary files (images, Office docs, PDF, etc.) return encoding: "base64"
  • workspace_write accepts both encodings — use "base64" for binary
  • Files written here are immediately available to all other skills in the session

Read the full file on GitHub · 71 lines

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. 4d ago First seen · 71 lines · 41 tokens per session scan A 791784d56ac8

Subscribe to this mod's changes

workspace is a skill published in the GitHub repository aws-samples/sample-strands-agent-with-agentcore (192 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 672 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 2026-08-30.