agentmods.dev

shared-workspace

shared-workspace is a skill for Claude Code from haowjy/creative-writing-skills. It costs 21 tokens per session (372 once invoked), scanned A, original, Apache-2.0.

A workspace-safety guide for agents working in directories that may contain other people's or agents' changes. It helps identify ownership and preserve unfamiliar files and edits.

In plain words
What is it for?
Use it before editing a shared project directory or after an interruption when you need to understand which files are safe to change.
Why use it?
It reduces the risk of overwriting active work, generated files, or changes whose owner is unclear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the creative-writing-skills plugin — 28 skills, 5 agents shipped together

not rated 567repo +13 10d ago A scan 21 tokens original Apache-2.0

Good fit Use it before editing a shared project directory or after an interruption when you need to understand which files are safe to change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/haowjy/creative-writing-skills/shared-workspace
View source ↗ haowjy/creative-writing-skills
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.

Any agent
npx skills add haowjy/creative-writing-skills --skill shared-workspace
Clone the repo
git clone --depth 1 https://github.com/haowjy/creative-writing-skills

Made for: Claude Code.

Or install creative-writing-skills, the plugin that ships this one along with the rest of its 28 skills, 5 agents.

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 shared-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/shared-workspace/github.svg)](https://agentmods.dev/skills/haowjy/creative-writing-skills/shared-workspace)
Your own site
<a href="https://agentmods.dev/skills/haowjy/creative-writing-skills/shared-workspace"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/shared-workspace/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 shared-workspace

Your own site · 80×15
<a href="https://agentmods.dev/skills/haowjy/creative-writing-skills/shared-workspace"><img src="https://agentmods.dev/badge/skills/haowjy/creative-writing-skills/shared-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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.
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 $0.00021 $0.00372
Opus 5.5 $0.00008 $0.00149
Sonnet 5.5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 10d ago against content hash 7264f565a98d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shared-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 10d 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.

plugin/claude/skills/shared-workspace/SKILL.md · 53 lines

What it actually says

Shared Workspace

You may be working in a directory that contains human or other-agent work you do not own. Treat unfamiliar files and edits as live work, not clutter.

Isolated workspaces reduce this risk, but they do not remove it: writers, reviewers, prompt editors, and cleanup tasks may still operate in shared directories.

Ownership is not always obvious. After compaction, interruption, or handoff, you may lose memory of files you created earlier. Use the current task, caller instructions, nearby artifacts, and file contents to infer ownership. When ownership is still unclear, preserve the file and report the uncertainty.

Orientation

Before editing:

  1. Identify where your outputs belong.
  2. Inspect nearby files enough to understand local conventions.
  3. Notice existing modified, generated, or unfamiliar files before changing the directory.
  4. Reconstruct ownership from task context and file evidence when memory is incomplete.

Orient to ownership, not cleanliness. A messy workspace may be active work.

Safety Rules

  • Preserve unfamiliar files and edits.
  • Keep generated artifacts, scratch files, logs, and captures contained.
  • If your task needs a clean environment, create an isolated workspace instead of cleaning the current one.
  • If your work overlaps existing changes you do not understand, stop and report the conflict.
  • If you cannot tell whether a file is yours after compaction or handoff, keep it and name the uncertainty in your report.

Reporting

When you finish, report:

  • files you intentionally changed
  • generated artifacts or logs you left behind
  • anything you avoided touching because ownership was unclear
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. 10d ago First seen · 53 lines · 21 tokens per session scan A 7264f565a98d

Subscribe to this mod's changes

shared-workspace is a skill published in the GitHub repository haowjy/creative-writing-skills (567 stars, last pushed 10d ago), licensed Apache-2.0. It adds 21 tokens to every session and 372 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 2026-10-28.

Git and workflow
Related

shared-workspace compared with skills from other repositories

shared-workspace next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shared-workspacehaowjy/creative-writing-skillsSkill56710d agoApache-2.0A21Claude Code
merge-batchdiegosouzapw/OmniRouteSkill83k6d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code