Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Check Writer Isolation

ASecurity

Verify one delegated writer changes only an isolated workspace while a separate observer remains read-only.

2 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agents

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add williamwue/oh-my-stack --skill check-writer-isolation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Check Writer Isolation?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Check Writer Isolation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-check-writer-isolation/badge)](https://www.skillsdirectory.com/skills/williamwue-check-writer-isolation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: check-writer-isolation
description: Verify one delegated writer changes only an isolated workspace while a separate observer remains read-only.
---

# Check Writer Isolation

Run this controlled fixture exactly once. Modify only the named fixture file.

1. Read the Skill-owned `assets/root.txt` and the project-owned
   `.oh-my-stack-eval/writer-isolation/writer.txt` from the root session.
   Retain the root marker and confirm the initial writer state is `base`.
2. Start one independent read-only observer. Ask it to read only
   `.oh-my-stack-eval/writer-isolation/writer.txt`, report
   `OBSERVED_STATE=base`, and make no changes.
3. Collect the observer result and independently confirm that the fixture file
   remains unchanged.
4. Establish exactly one runtime isolation boundary for the writer:
   - Treat the root session's starting checkout as the source checkout by
     default. A temporary directory, or a path different from the project that
     authored this Skill, is not evidence of runtime isolation.
   - If the root session already runs in a runtime-managed checkout that is
     proven distinct from another checkout for this probe at the same revision
     and containing the same fixture, delegate the writer into that current
     checkout. Do not create a nested checkout or invoke an external workspace
     manager.
   - Otherwise, request the runtime's isolated workspace when starting the
     writer.
   Ask the writer to change only
   `.oh-my-stack-eval/writer-isolation/writer.txt`, replacing
   `WRITER_STATE=base` with `WRITER_STATE=isolated-ok`. It must report its
   workspace path and exact changed file.
5. Collect the writer result. Do not start another writer and do not manually
   reproduce its edit in the root session.
6. Independently verify the exact one-line change using the isolated workspace
   or its returned patch or revision. Confirm that no other tracked file
   changed and that the source checkout was not modified before an explicit
   transfer boundary.
7. Read `assets/root.txt` again. Report the observer state, writer isolation
   evidence, exact changed path, final writer state or retained patch state,
   source-checkout state, root marker, and any unexpected changes.

Attribution

williamwuewilliamwue
View sourceSee grades on GitHubMore from williamwue →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →