Never Ask Again — Development skill for Claude Code
Permission allowlists for Claude Code and Codex, so your agent stops asking and still cannot nuke your laptop.
How to install Never Ask Again
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open josipledic/never-ask-again and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Never Ask Again does
Permission allowlists for Claude Code and Codex, so your agent stops asking and still cannot nuke your laptop.
Alternatives in Development
- Understand Anything — Graphs that teach graphs that impress 80.7k ★
- Understand Anything — Claude Code skills that turn any codebase into an interactive knowledge graph you can explore, search, and ask 2.5k ★
- Clawk — Give coding agents a disposable Linux VM, not your laptop 996 ★
README
never-ask-again
Permission allowlists for AI coding agents, so yours stops asking
and still cannot nuke your laptop.
[](https://github.com/josipledic/never-ask-again/actions/workflows/ci.yml)    
Every coding agent ships a permission prompt, and every one of them gets tedious by the third `npm test`. So people flip on the bypass flag and hand an LLM unreviewed root on their working machine.
This is the middle setting. Around a thousand rules covering 20 ecosystems, sorted into three buckets, generated into the config format each agent actually reads.
allow = reversible and local
ask = touches remote state or installs code
deny = destroys, escalates, or exfiltrates`terraform plan` runs. `terraform apply` asks. `terraform state rm` never runs at all.
Supported agents
| Agent | Config file | Generated | Granularity |
|---|---|---|---|
| Bob | ~/.bob/settings/settings.json |
`dist/bob/settings.json` | prefix match |
| Claude Code | ~/.claude/settings.json |
`dist/claude/settings.json` | full arguments |
| Codex | ~/.codex/rules/default.rules |
`dist/codex/default.rules` | full argv |
| OpenCode | ~/.config/opencode/opencode.json |
`dist/opencode/opencode.json` | full arguments |
| Oh My Pi | `~/.omp/agent/config.yml |
Related Skills
Claude MCP Allow
Generate least-privilege Claude Code permission rules for MCP tools from their live annotations: readOnlyHint
Thumbgate Guard
Turn the last agent mistake into a hard prevention rule the agent cannot bypass. Use after a bad tool call, a
Autonomize
Autonomous execution under user's permission envelope. Recommend the optimal, root-cause, long-term fix with e
Ask Questions Skill
Agent Skill for asking sharper, more useful clarifying questions instead of guessing.
Mod Maker
Mod Maker: find what you ask Claude Code again and again, and turn it into a mod. Plus 8 example mods and a vi
Rot Moe Install
Install the RoT MoE plugin from this clone -- verify the tree, arm the router, prove it is running. Never elev
Related Agents
Swe Dev Change Assurance Engineer
Reviews consequential changes by asking which prior claims and evidence still apply, what became stale or cont
Maker Decomposition Discriminator
MAKER Decomposition Discriminator - Validates task decompositions. MUST BE USED AUTOMATICALLY after maker-deco
Permissions Manager
Manage tool permission rules. Use when user says 'allow', 'deny', or 'ask' for a command, wants to modify perm
