safety/permission-gate SKILL.md skillA

safety/permission-gate from frankxai/starlight-intelligence-system is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add frankxai/starlight-intelligence-system/safety/permission-gate@git:20260611.98409d1

Pins git:20260611.98409d1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
frankxai/starlight-intelligence-system
Path
skills/safety/permission-gate/SKILL.md
Versions recorded
1
Latest version
git:20260611.98409d1, committed Jun 11, 2026
Size
2,777 bytes
Repository stars
10
License
MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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

1. Receive permission request: `{ claw_id, action_type, target, declared_reason }`
2. Load the requesting Claw's `CLAW.md` permission block
3. 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, return
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add frankxai/starlight-intelligence-system/safety/permission-gate@sha256:aca0aa93be6f245a

The line at the top of this page pins the label git:20260611.98409d1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_x75wdbguda4op5nu.svg)](https://markdownregistry.com/a/art_x75wdbguda4op5nu)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jun 11, 2026.

versioncommittedcommitsizeaudit
git:20260611.98409d1 latest2026-06-11 98409d1 2,777 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2777 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

frankxai/starlight-intelligence-system · 10 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_x75wdbguda4op5nu
GET https://markdownregistry.com/api/v1/resolve?ref=frankxai/starlight-intelligence-system/safety/permission-gate
GET https://markdownregistry.com/api/v1/blob/aca0aa93be6f245a973a79efb0edaf1966db6e158b1d117def75e86aa9c04d86

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from frankxai/starlight-intelligence-system

frank-brand-editor SKILL.md skill
frankxai/starlight-intelligence-system · .agents/skills/frank-brand-editor/SKILL.md · Use for any public copy in this repository. Load CREATOR.md, preserve facts and search intent, and run the Starlight…
git:20260906.3f9f53e · audit A · 10 stars
CLAUDE.md@.claude/hooks CLAUDE.md file
frankxai/starlight-intelligence-system · .claude/hooks/CLAUDE.md
git:20260624.02f6cdc · audit A · 10 stars
agent-hygiene SKILL.md skill
frankxai/starlight-intelligence-system · .claude/skills/agent-hygiene/SKILL.md · The quality bar for any agent working on agent definitions, skills, commands, hooks, AGENTS.md or CLAUDE.md, in any…
v1.0.0 · audit A · 10 stars
estate-guard SKILL.md skill
frankxai/starlight-intelligence-system · .claude/skills/estate-guard/SKILL.md · Security gate for agentic repos. Use before opening a PR that touches .github/workflows, .claude (hooks, settings…
git:20261005.c462fc7 · audit C · 10 stars
editorial Cursor rule
frankxai/starlight-intelligence-system · .cursor/rules/editorial.mdc · Portfolio brand and editorial contract
git:20260906.3f9f53e · audit A · 10 stars
starlight-agents Cursor rule
frankxai/starlight-intelligence-system · .cursor/rules/starlight-agents.mdc · Starlight Agent Activation Rules
git:20260210.91eef05 · audit A · 10 stars
starlight-core Cursor rule
frankxai/starlight-intelligence-system · .cursor/rules/starlight-core.mdc · Starlight Intelligence System - Core Rules
git:20261011.34dcd43 · audit A · 10 stars
starlight-memory Cursor rule
frankxai/starlight-intelligence-system · .cursor/rules/starlight-memory.mdc · Starlight Vault and Memory Rules
git:20260210.91eef05 · audit A · 10 stars
starlight-voice Cursor rule
frankxai/starlight-intelligence-system · .cursor/rules/starlight-voice.mdc · Starlight voice for branded copy and agent dialogue
git:20261013.a0065c3 · audit A · 10 stars
excellence-review SKILL.md skill
frankxai/starlight-intelligence-system · .grok/skills/excellence-review/SKILL.md · Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso…
git:20260613.efb4f56 · audit A · 10 stars
harness-integration SKILL.md skill
frankxai/starlight-intelligence-system · .grok/skills/harness-integration/SKILL.md · ACOS Grok bridge. SessionStart loads repo-mastery + excellence gates. PreToolUse enforces rules read + suggests harness…
git:20261001.4020877 · audit A · 10 stars
multi-harness-orchestrator SKILL.md skill
frankxai/starlight-intelligence-system · .grok/skills/multi-harness-orchestrator/SKILL.md · Automatically detect tasks suited for delegation to other agent harnesses (Claude Code as canonical, agy/antigravity…
git:20260613.efb4f56 · audit A · 10 stars

Every file in frankxai/starlight-intelligence-system

Browse by kind, by grade A, or by owner.