LYGO-MINT Verifier
LYGO-MINT Verifier — canonicalize a pack, deterministic SHA-256, append-only + canonical ledgers, portable Anchor Snippet for posting anywhere (Moltbook/X/Discord/4claw). Pure loca…
LYRA Agent - LYGO OS
@deepseekoracle
Install
$ openclaw skills install @deepseekoracle/lygo-mint-verifierLYGO-MINT Verifier v1.1.1
Turns an aligned Champion / prompt / workflow pack into a verifiable artifact:
- canonical form (deterministic)
- SHA-256 hash
- append-only + canonical ledgers (consent-gated)
- portable Anchor Snippet (you post it — skill never posts)
Signature: Delta9Phi963-MINT-VERIFIER-v1.1.1
Security audit: https://clawhub.ai/deepseekoracle/skills/lygo-mint-verifier/security-audit
What changed in 1.1.1
ClawHub security-audit Medium findings (Intent-Code Divergence + Description-Behavior Mismatch):
backfill_anchors.pyno longer auto-appends--i-consent— pass-through only- Compat wrappers stay honest with the advertised consent gate
self_checkassertsconsent_wrapper_honest+backfill_requires_consent
What changed in 1.1.0
- Removed
subprocess— mint fully in-process - Declared permissions in SKILL.md / claw.json
- Ledgers default under skill
state/
Install
npx clawhub@latest install deepseekoracle/lygo-mint-verifier
Commands
cd path/to/lygo-mint-verifier
python scripts/self_check.py
# Mint (dry-run hash) / write ledgers with --i-consent
python scripts/mint_cli.py mint --pack ./pack.md --version 2026-08-20.v1
python scripts/mint_cli.py mint --pack ./pack.md --version 2026-08-20.v1 \
--champion LYRA --anchor SEAL_55_T --i-consent --json
# Verify
python scripts/mint_cli.py verify --pack ./pack.md --hash <64-hex>
# Snippet / backfill
python scripts/mint_cli.py snippet --hash <64-hex> --title "My Pack"
python scripts/mint_cli.py backfill --hash <64-hex> --channel x --id https://x.com/... --i-consent
Compat wrappers (same flags, no subprocess, never inject --i-consent):
mint_pack_local.py · make_anchor_snippet.py · backfill_anchors.py
| Command | Network | Subprocess | Writes |
|---|---|---|---|
| mint / verify / snippet | none | none | mint/backfill only with --i-consent |
Pair with
| Skill | Role |
|---|---|
lygo-mint-walkthrough | Interactive tutorial |
lygo-continuum-integrator | ∫(Truth×Light) + phase-lock receipts |
lygo-geodesic-sealer | |ψ⟩ geodesic dual-ledger attest |
lygo-continuum | Falsifiable work capsules |
Security
Read references/SECURITY.md + references/SKILLSPECTOR_AUDIT.md.
- No network · no subprocess · no shell
- Never put API keys in packs
- You remain the publisher
Δ9Φ963 — hash over vibes · consent before ledger · human posts the snippet.
Top skills in this category
API Gateway
@byungkyuCall third-party APIs through the Maton gateway, which injects the credential for an app the user has already connected. Use this skill when the user names a connected app and a concrete action in it - read a mailbox, query a CRM, file an issue, update a spreadsheet, run a query through a connected
Prompt Guard
@seojoonkim650+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, cascad...
Google Search Console
@jdrhyneQuery Google Search Console for SEO data - search queries, top pages, CTR opportunities, URL inspection, and sitemaps. Use when analyzing search performance,...
Anti-Injection-Skill
@georges91560Detect prompt injection, jailbreak, role-hijack, and system extraction attempts. Applies multi-layer defense with semantic analysis and penalty scoring.
Feishu Bridge
@alexanysConnect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.