Skill Trust — Development skill for Claude Code
Grant, revoke, or list trust for skill-trace sources (gates sync into the global store, and future injection).
How to install Skill Trust
Installs to ~/.claude/skills/crackcode09-skill-trace-skill-trust/SKILL.md
mkdir -p ~/.claude/skills/crackcode09-skill-trace-skill-trust && curl -fsSL https://raw.githubusercontent.com/crackcode09/skill-trace/HEAD/commands/skill-trust.md -o ~/.claude/skills/crackcode09-skill-trace-skill-trust/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Trust does
description: Grant, revoke, or list trust for skill-trace sources (gates sync into the global store, and future injection) argument-hint: "[grant|revoke|list] [project-slug]" allowed-tools: Bash(node:*)
The skill-trace trust registry decides which projects may have their lessons **synced into the global store** (and, later, injected into sessions). Every project keeps its own lessons locally regardless. The sync hook records every source as untrusted; only an explicit grant here (or a m
Alternatives in Development
- Internet Court Skill — The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 4.9k ★
- CORS — Scan an endpoint for CORS misconfiguration — arbitrary-origin reflection, null-origin trust, credential exposu 4.5k ★
- Academic Pptx Skill — A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant b 811 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ldd Autonomy Ack
Pre-grant, list, check, or revoke autonomy acks so architect-mode's creativity=inventive can fire in autonomou
Sync Context
Manual cross-project sync between local .agent-memory/ and the global ~/.claude-memory/global/ store — privacy
Skill Trace
Manage this project's skill-trace lesson store — forget a lesson, run a sync by hand, or show status
Knowledge Ops
Use when explicitly asked to add, edit, delete, list, or sync indexed knowledge sources for Lumina through the
Hermesh
Let personal agents drive coding agents on your own machines, with every grant signed on a device you trust
Skillmem
Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memo
Related Agents
Explore Leg
Read-only-charge Opus exploration/derivation leg — censuses, sweeps, searches, state derivation across many fi
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,
Security Architecture
Boucle implements a defense-in-depth security model to protect against prompt injection attacks and maintain t