taehwandev/tao-agent-os/agent-editing-safety
Claude Code and agent skill by taehwandev/tao-agent-os
- community
Checking that the SKILL.md file is still in the repository.
Agent Editing Safety: Use this when an agent may edit files, run commands, inspect local state, or touch data outside the current repository.
Install
npx vskill@latest install taehwandev/tao-agent-os/agent-editing-safetySKILL.md
The same SKILL.md was published earlier as taehwandev/tao-agent-os/agent-editing-safety.
Agent Editing Safety
Use when routed to common/skills/agent-editing-safety/SKILL.md or when work needs this Moru Core guidance area.
Read
references/current-guidance.mdfor the detailed guidance for this skill.- Related
SKILL.mdentrypoints named by the reference before loading their detailed references.
Process
- Read this entrypoint first to confirm this guidance area applies.
- Open
references/current-guidance.mdonly when the task actually touches this area. - Follow the reference's decision rules, stop conditions, and verification requirements before editing, reviewing, or reporting completion.
Do Not
- Do not look for legacy flat compatibility paths; load this skill bundle as the canonical context-loading target.
- Do not load broad references for unrelated work just because this skill was nearby in the route.
- Do not report a zero-reference result from an ignore-aware searcher. Before a
delete, rename, or migration, answer "is anything still referencing this?" with an ignore-unaware sweep (/usr/bin/grep -r, or rg --no-ignore --hidden) and name which searcher produced the count. A shell grep may be a wrapper that skips gitignored and hidden paths, so its silence is not evidence of absence.
Verification
- If route wiring changes, confirm the route loads this
SKILL.mdentrypoint. - If detailed guidance changes, validate links and frontmatter for
references/current-guidance.md. - If a reference sweep decides a removal, state the searcher used and its count;
a bare zero from an ignore-aware tool does not clear the check.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcommon/skills/agent-editing-safety/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/taehwandev/tao-agent-os/agent-editing-safety)