How do I install the Safety/permission Gate skill?

Run npx skillmds@latest add frankxai/safety-permission-gate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Safety/permission Gate safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Safety/permission Gate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Safety/permission Gate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Safety/permission Gate?

frankxai (@frankxai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Safety/permission Gate by frankxai — Agent Skill

Name: Safety/permission Gate
Author: frankxai

Safety/permission Gate

Gate every mutation request against the Claw's declared permission surface — fires before any write to filesystem, vault, or external system. No Claw bypasses this gate. Default skill for Starlight Sentinel and every Claw that carries filesystem or sis_vaults write permissions.

frankxai Updated Sep 17, 2026

File contents

Permission Gate

Every mutation request passes through this gate. No Claw bypasses it.

When This Skill Activates

Any Claw attempts to write files, execute shell commands, or export data
Keywords: "write", "move", "delete", "execute", "export", "send", "upload"
Always active when Sentinel Claw is running
Default for: Starlight Sentinel

What This Skill Does

Evaluates permission requests from Claws against their declared permission surface in CLAW.md, the user's workspace contract, and the active safety posture. Issues a programmatic APPROVE or DENY with logged reasoning.

Procedures

Procedure 1: Permission Evaluation

Receive permission request: { claw_id, action_type, target, declared_reason }
Load the requesting Claw's CLAW.md permission block
Check: is the requested action within the Claw's declared permissions.* surface?
Check: is the target path within the declared workspace?
Check: does the Claw's mutation_default allow this action without explicit approval?
If mutation_default: false → escalate to Procedure 2 (Mutation Approval Request)
If within permissions + mutation_default: true → APPROVE, log, return
If outside permissions → DENY, log reason, return

Procedure 2: Permission Boundary Violation

Action requested is outside declared permission surface
Log violation: { timestamp, claw_id, requested_action, declared_surface, verdict: DENY }
Present violation to user in plain language
Offer: "Update Claw contract to include this permission?" or "Proceed as one-time exception?"
Never auto-approve boundary violations

Procedure 3: Permission Log Write

Every decision (APPROVE or DENY) writes to ~/.starlight/logs/permission.jsonl
Entry includes: timestamp, claw_id, action_type, target (sanitized), decision, reason
Log is append-only — no entry is ever modified or deleted

Integration Points

Vaults: Reads Wisdom vault for security principles
Agents: Primary agent is Starlight Sentinel
Claws: Called by every Claw with requires_sentinel: true
Skills: Composes with mutation-approval for interactive approval flows

Quality Criteria

Every mutation is logged before it executes
Boundary violations are surfaced to the user, never silently resolved
DENY decisions include a human-readable reason
Log entries are parseable JSON (not freeform text)

---name: safety-permission-gatedescription: Gate every mutation request against the Claw's declared permission surface — fires before any write to filesystem, vault, or external system. No Claw bypasses this gate. Default skill for Starlight Sentinel and every Claw that carries filesystem or sis_vaults write permissions.---# Permission Gate> Every mutation request passes through this gate. No Claw bypasses it.## When This Skill Activates- Any Claw attempts to write files, execute shell commands, or export data- Keywords: "write", "move", "delete", "execute", "export", "send", "upload"- Always active when Sentinel Claw is running- Default for: Starlight Sentinel## What This Skill DoesEvaluates permission requests from Claws against their declared permission surface in `CLAW.md`, the user's workspace contract, and the active safety posture. Issues a programmatic APPROVE or DENY with logged reasoning.## Procedures### Procedure 1: Permission Evaluation1. Receive permission request: `{ claw_id, action_type, target, declared_reason }`2. Load the requesting Claw's `CLAW.md` permission block3. Check: is the requested action within the Claw's declared `permissions.*` surface?4. Check: is the target path within the declared workspace?5. Check: does the Claw's `mutation_default` allow this action without explicit approval?6. If `mutation_default: false` → escalate to Procedure 2 (Mutation Approval Request)7. If within permissions + `mutation_default: true` → APPROVE, log, return8. If outside permissions → DENY, log reason, return### Procedure 2: Permission Boundary Violation1. Action requested is outside declared permission surface2. Log violation: `{ timestamp, claw_id, requested_action, declared_surface, verdict: DENY }`3. Present violation to user in plain language4. Offer: "Update Claw contract to include this permission?" or "Proceed as one-time exception?"5. Never auto-approve boundary violations### Procedure 3: Permission Log Write1. Every decision (APPROVE or DENY) writes to `~/.starlight/logs/permission.jsonl`2. Entry includes: timestamp, claw_id, action_type, target (sanitized), decision, reason3. Log is append-only — no entry is ever modified or deleted## Integration Points- **Vaults:** Reads Wisdom vault for security principles- **Agents:** Primary agent is Starlight Sentinel- **Claws:** Called by every Claw with `requires_sentinel: true`- **Skills:** Composes with `mutation-approval` for interactive approval flows## Quality Criteria- Every mutation is logged before it executes- Boundary violations are surfaced to the user, never silently resolved- DENY decisions include a human-readable reason- Log entries are parseable JSON (not freeform text)

Frequently asked questions