[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76Y5RN57VHVJS6TQQCTYRNT":3,"skill-same:01M76Y5RN57VHVJS6TQQCTYRNT":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":59},"01M76Y5RN57VHVJS6TQQCTYRNT","agent-passport",null,"OAuth for the agentic era. Consent-gating for ALL sensitive agent actions. 75+ data-driven threat definitions with auto-updates (like antivirus signatures). Includes Skill Scanner, Injection Shield, SSRF Shield, Path Traversal Guard, spending caps, rate limits, allowlists, TTL expiry, audit trails, and KYA metadata. Pro tier adds real-time threat definition updates every 6 hours.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fagent-passport\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: agent-passport\nversion: 2.4.0\ndescription: \"OAuth for the agentic era. Consent-gating for ALL sensitive agent actions. 75+ data-driven threat definitions with auto-updates (like antivirus signatures). Includes Skill Scanner, Injection Shield, SSRF Shield, Path Traversal Guard, spending caps, rate limits, allowlists, TTL expiry, audit trails, and KYA metadata. Pro tier adds real-time threat definition updates every 6 hours.\"\nmetadata: {\"openclaw\":{\"requires\":{\"bins\":[\"jq\",\"bc\",\"xxd\",\"head\",\"date\",\"mkdir\"],\"env\":[\"AGENT_PASSPORT_LEDGER_DIR\"]}}}\nuser-invocable: true\n---\n\n# Agent Passport (OpenClaw)\n\n## 30-Second Setup\n\n```bash\n# Initialize and register your agent\n.\u002Fmandate-ledger.sh init agent:my-assistant \"Your Name\" \"personal assistant\" \"openclaw\"\n\n# Grant dev tool access (git, npm, docker, etc.)\n.\u002Fmandate-ledger.sh create-from-template dev-tools\n\n# That's it! The agent will now check permissions before sensitive actions.\n```\n\n> **Templates available:** `dev-tools` · `email-team \u003Cdomain>` · `file-ops \u003Cpath>` · `web-research` · `safe-browsing` · `coding` · `email-assistant` · `read-only` · `full-auto`\n> Run `.\u002Fmandate-ledger.sh templates` to see all options.\n\n---\n\n## ⚡ Agent Behavioral Contract\n\n**If you are an agent reading this skill, these are your rules. Follow them.**\n\n### When to Check\n\nBefore performing ANY of these actions, you MUST call `check-action` first:\n\n| Action | Category | Example target |\n|--------|----------|----------------|\n| Running a shell command | `system` | `\"git pull\"`, `\"npm install\"` |\n| Sending a message\u002Femail | `communication` | `\"bob@company.com\"` |\n| Writing\u002Fdeleting a file | `data` | `\"\u002Fpath\u002Fto\u002Ffile.txt\"` |\n| Making an API call with side effects | `external_api` | `\"api.github.com\"` |\n| Spending money | `financial` | `\"merchant_amazon\"` with amount |\n| Acting publicly as the user | `identity` | `\"twitter_post\"` |\n\n**You do NOT need to check:** reading files, web searches, internal reasoning, or anything with no side effects.\n\n### How to Check\n\n```bash\nSCRIPT_DIR=\"$HOME\u002F.openclaw\u002Fskills\u002Fagent-passport\u002Fscripts\"\n\nresult=$($SCRIPT_DIR\u002Fmandate-ledger.sh check-action \"\u003Cyour_agent_id>\" \"\u003Ccategory>\" \"\u003Ctarget>\" [amount])\n```\n\nParse the result:\n- `authorized: true` → proceed, then log the action afterward\n- `authorized: false` → **STOP. Ask the user.**\n- If response includes `kill_switch: true` or reason `Kill switch engaged` → **STOP immediately** and ask user to run `mandate-ledger.sh unlock`\n\n### The Flow\n\n```\n1. You want to do something sensitive\n2. Call check-action\n3. IF authorized:\n   a. Do the thing\n   b. Log it: mandate-ledger.sh log-action \u003Cmandate_id> \u003Camount> \"\u003Cdescription>\"\n4. IF denied:\n   a. Tell the user what you want to do and why\n   b. Suggest a mandate (show scope, duration, constraints)\n   c. Wait for approval\n   d. If approved, create the mandate, then proceed\n```\n\n### How to Ask for Permission\n\nWhen denied, present it clearly and concisely:\n\n```\nI need to [ACTION] but don't have a mandate for it.\n\n📋 [CATEGORY]: [what you want to do]\n🎯 Target: [specific target]\n⏰ Suggested duration: [reasonable TTL]\n\nWant me to set this up? I can also create a broader mandate if you'd\nprefer (e.g., all emails to @company.com for 30 days).\n```\n\n**DO NOT:**\n- Bypass the check and do it anyway\n- Ask repeatedly for the same thing if denied\n- Create mandates yourself without user approval\n- Pretend you checked when you didn't\n\n**DO:**\n- Suggest templates when appropriate (\"Want me to set up `dev-tools`?\")\n- Batch similar requests (\"I'll need to run several git commands — want a dev-tools mandate?\")\n- Log every action after completion\n- Mention remaining limits when relevant (\"3\u002F20 daily emails used\")\n\n### First-Time Setup\n\nIf `check-action` returns `\"hint\": \"templates\"`, the ledger is empty. Guide the user:\n\n```\nAgent Passport isn't set up yet. It takes 30 seconds:\n\n  mandate-ledger.sh init agent:me \"Your Name\" \"assistant\" \"openclaw\"\n  mandate-ledger.sh create-from-template dev-tools\n\nWant me to run this for you?\n```\n\n### Logging Actions\n\nAfter every authorized action, log it:\n\n```bash\n$SCRIPT_DIR\u002Fmandate-ledger.sh log-action \"\u003Cmandate_id>\" \u003Camount> \"\u003Cdescription>\"\n```\n\n- For financial: amount = dollars spent\n- For everything else: amount = 1\n- Description should be human-readable: \"Sent email to bob@company.com re: Q1 report\"\n\n### Kill Switch Behavior\n\nIf the user engages the kill switch, all operations are frozen until unlocked.\n\n```bash\n.\u002Fmandate-ledger.sh kill \"user requested freeze\"\n.\u002Fmandate-ledger.sh unlock\n```\n\nAgent behavior when kill switch is active:\n- Do not attempt sensitive actions\n- Do not retry `check-action` in a loop\n- Tell user operations are blocked and request explicit `unlock`\n\n---\n\n## Overview\n\nAgent Passport provides a consent layer for agent autonomy. Instead of all-or-nothing permissions, users grant **mandates** with specific constraints:\n\n```\n\"I authorize this agent to [ACTION] with [CONSTRAINTS] until [EXPIRY]\"\n```\n\nThis isn't just about purchases — it's consent-gating for **all sensitive actions**.\n\n## Action Categories\n\n| Category | Examples | Typical Constraints |\n|----------|----------|---------------------|\n| `financial` | Purchases, transfers, subscriptions | Spending cap, merchant allowlist |\n| `communication` | Emails, messages, tweets, posts | Recipient allowlist, rate limit |\n| `data` | Delete files, edit docs, DB writes | Path allowlist, require backup |\n| `system` | Shell commands, installs, configs | Command allowlist, no sudo |\n| `external_api` | Third-party API calls | Service allowlist, rate limit |\n| `identity` | Public actions \"as\" the user | Human review required |\n\n## Wildcard Patterns\n\nAllowlists and deny lists support three wildcard styles:\n\n| Pattern | Matches | Example |\n|---------|---------|---------|\n| `prefix *` | Anything starting with prefix | `git *` → `git pull`, `git status` |\n| `*.suffix` | Anything ending with suffix | `*.env` → `config.env`, `.env` |\n| `*middle*` | Anything containing middle | `*\u002F.git\u002F*` → `repo\u002F.git\u002Fconfig` |\n| `*@domain` | Email domain match | `*@company.com` → `bob@company.com` |\n| `exact` | Exact match only | `api.github.com` |\n\n## Modes\n\n- **Local mode** (default): Mandates stored in `~\u002F.openclaw\u002Fagent-passport\u002F`. Free tier is fully offline. Pro tier makes periodic API calls to `api.agentpassportai.com` for license validation and threat definition updates.\n- **Preview mode:** No storage, no network. Generates validated payloads and curl templates.\n- **Live mode (roadmap):** Future connection to Agent Bridge backend for multi-agent sync and compliance. Not yet implemented.\n\n## Quick Start Commands\n\n```bash\n# Initialize with identity\n.\u002Fmandate-ledger.sh init \u003Cagent_id> \u003Cprincipal> [scope] [provider]\n\n# Templates (auto-detects agent if registered)\n.\u002Fmandate-ledger.sh templates\n.\u002Fmandate-ledger.sh create-from-template dev-tools\n.\u002Fmandate-ledger.sh create-from-template email-team \u003Cdomain>\n.\u002Fmandate-ledger.sh create-from-template file-ops \u003Cpath>\n.\u002Fmandate-ledger.sh create-from-template web-research\n.\u002Fmandate-ledger.sh create-from-template safe-browsing\n.\u002Fmandate-ledger.sh create-from-template coding\n.\u002Fmandate-ledger.sh create-from-template email-assistant\n.\u002Fmandate-ledger.sh create-from-template read-only\n.\u002Fmandate-ledger.sh create-from-template full-auto\n\n# Quick create (human-friendly durations: 7d, 24h, 30m)\n.\u002Fmandate-ledger.sh create-quick \u003Ctype> \u003Cagent_id> \u003Callowlist_csv> \u003Cduration> [amount_cap]\n\n# Check & log\n.\u002Fmandate-ledger.sh check-action \u003Cagent> \u003Ctype> \u003Ctarget> [amount]\n.\u002Fmandate-ledger.sh log-action \u003Cmandate_id> \u003Camount> \"\u003Cdescription>\"\n\n# Audit\n.\u002Fmandate-ledger.sh audit [limit]\n.\u002Fmandate-ledger.sh summary\n\n# Threat definitions\n.\u002Fmandate-ledger.sh init-definitions\n.\u002Fmandate-ledger.sh update-definitions\n.\u002Fmandate-ledger.sh definitions-status\n```\n\n## Commands Reference\n\n### Quick Start\n```bash\ninit [agent_id] [principal] [scope] [provider]\n                           # Initialize ledger, optionally register agent\ntemplates                  # List available templates\ncreate-from-template \u003Ct>   # Create mandate from template\n  [agent_id] [args...]\ncreate-quick \u003Ctype>        # Create with positional args\n  \u003Cagent_id> \u003Callowlist>\n  \u003Cduration> [amount_cap]\n```\n\n### Mandate Lifecycle\n```bash\ncreate \u003Cjson>              # Create mandate (include action_type)\ncreate-with-kya \u003Cjson>     # Create with auto-attached agent KYA\nget \u003Cmandate_id>           # Get mandate by ID\nlist [filter]              # List mandates (all|active|revoked|\u003Caction_type>)\nrevoke \u003Cmandate_id> [why]  # Revoke a mandate\n```\n\n### Authorization\n```bash\ncheck-action \u003Cagent> \u003Ctype> \u003Ctarget> [amount]\n                           # Check if action is authorized\nlog-action \u003Cmandate_id> \u003Camount> [description]\n                           # Log action against mandate\nkill \u003Creason>               # Engage kill switch and freeze execution\nunlock                      # Disengage kill switch\n```\n\n### Audit & Reporting\n```bash\naudit [limit]              # Show recent audit entries\naudit-mandate \u003Cid>         # Show audit for specific mandate\naudit-summary [since]      # Summary by action type\nsummary                    # Show overall ledger stats\nexport                     # Export full ledger as JSON\n```\n\n### Threat Definitions\n```bash\ninit-definitions           # Write bundled threat-definitions.json to LEDGER_DIR\nupdate-definitions         # Refresh definitions (Pro: API pull, Free: bundled copy)\n  [--force] [--offline]\ndefinitions-status         # Show version, pattern counts, and last update\n```\n\n### KYA (Know Your Agent)\n```bash\nkya-register \u003Cagent_id> \u003Cprincipal> \u003Cscope> [provider]\nkya-get \u003Cagent_id>\nkya-list\nkya-revoke \u003Cagent_id> [why]\n```\n\n## Mandate Structure\n\n```json\n{\n  \"mandate_id\": \"mandate_1770412575_3039e369\",\n  \"action_type\": \"communication\",\n  \"agent_id\": \"agent:my-assistant\",\n  \"scope\": {\n    \"allowlist\": [\"*@mycompany.com\", \"bob@partner.com\"],\n    \"deny\": [\"*@competitor.com\"],\n    \"rate_limit\": \"20\u002Fday\",\n    \"kya\": { \"status\": \"verified\", \"verified_principal\": \"Mark\" }\n  },\n  \"amount_cap\": null,\n  \"ttl\": \"2026-02-13T00:00:00Z\",\n  \"status\": \"active\",\n  \"usage\": { \"count\": 5, \"total_amount\": 0 },\n  \"created_at\": \"2026-02-06T22:00:00Z\"\n}\n```\n\n## Agent Bridge (Future Roadmap)\n\n> **Note:** Free tier is fully local with no network calls. Pro tier (`AGENT_PASSPORT_LICENSE_KEY` set) makes periodic HTTPS calls to `api.agentpassportai.com` for license validation and threat definition updates. No usage data or scan results are transmitted. Agent Bridge is a planned future service.\n\nLocal mode handles single-user, single-agent scenarios. A future Agent Bridge service would add:\n\n- **Multi-agent coordination** — prevent overlapping mandates\n- **Cross-device sync** — same mandates everywhere\n- **Organization policies** — IT guardrails, user customization within\n- **Compliance reporting** — audit exports for regulatory needs\n- **Merchant\u002Fservice registry** — verified vendors, trust scores\n\nExport local ledger anytime: `.\u002Fmandate-ledger.sh export > backup.json`\n\n## Configuration (OpenClaw)\n\n```json\n{\n  \"skills\": {\n    \"entries\": {\n      \"agent-passport\": {\n        \"env\": {\n          \"AGENT_PASSPORT_LOCAL_LEDGER\": \"true\"\n        },\n        \"config\": {\n          \"default_currency\": \"USD\",\n          \"default_ttl_minutes\": 60,\n          \"confirm_threshold_amount\": 50\n        }\n      }\n    }\n  }\n}\n```\n\n## Storage\n\nAll data stored locally in `~\u002F.openclaw\u002Fagent-passport\u002F`:\n- `mandates.json` — mandate ledger\n- `agents.json` — KYA registry\n- `audit.json` — action audit trail\n- `threat-definitions.json` — active threat pattern definitions\n- `threat-definitions.bak` — previous definitions backup\n- `.threat-meta.json` — last update\u002Fversion\u002Fsource metadata\n\n## Safety\n\n- Never leak secrets into prompts, logs, or outputs\n- Mandates constrain actions, but don't prevent all misuse\n- Audit trail provides accountability, not prevention\n- Use KYA to verify agent identity before granting broad mandates\n","# Agent Passport (OpenClaw)\n\n## 30-Second Setup\n\n```bash\n# Initialize and register your agent\n.\u002Fmandate-ledger.sh init agent:my-assistant \"Your Name\" \"personal assistant\" \"openclaw\"\n\n# Grant dev tool access (git, npm, docker, etc.)\n.\u002Fmandate-ledger.sh create-from-template dev-tools\n\n# That's it! The agent will now check permissions before sensitive actions.\n```\n\n> **Templates available:** `dev-tools` · `email-team \u003Cdomain>` · `file-ops \u003Cpath>` · `web-research` · `safe-browsing` · `coding` · `email-assistant` · `read-only` · `full-auto`\n> Run `.\u002Fmandate-ledger.sh templates` to see all options.\n\n---\n\n## ⚡ Agent Behavioral Contract\n\n**If you are an agent reading this skill, these are your rules. Follow them.**\n\n### When to Check\n\nBefore performing ANY of these actions, you MUST call `check-action` first:\n\n| Action | Category | Example target |\n|--------|----------|----------------|\n| Running a shell command | `system` | `\"git pull\"`, `\"npm install\"` |\n| Sending a message\u002Femail | `communication` | `\"bob@company.com\"` |\n| Writing\u002Fdeleting a file | `data` | `\"\u002Fpath\u002Fto\u002Ffile.txt\"` |\n| Making an API call with side effects | `external_api` | `\"api.github.com\"` |\n| Spending money | `financial` | `\"merchant_amazon\"` with amount |\n| Acting publicly as the user | `identity` | `\"twitter_post\"` |\n\n**You do NOT need to check:** reading files, web searches, internal reasoning, or anything with no side effects.\n\n### How to Check\n\n```bash\nSCRIPT_DIR=\"$HOME\u002F.openclaw\u002Fskills\u002Fagent-passport\u002Fscripts\"\n\nresult=$($SCRIPT_DIR\u002Fmandate-ledger.sh check-action \"\u003Cyour_agent_id>\" \"\u003Ccategory>\" \"\u003Ctarget>\" [amount])\n```\n\nParse the result:\n- `authorized: true` → proceed, then log the action afterward\n- `authorized: false` → **STOP. Ask the user.**\n- If response includes `kill_switch: true` or reason `Kill switch engaged` → **STOP immediately** and ask user to run `mandate-ledger.sh unlock`\n\n### The Flow\n\n```\n1. You want to do something sensitive\n2. Call check-action\n3. IF authorized:\n   a. Do the thing\n   b. Log it: mandate-ledger.sh log-action \u003Cmandate_id> \u003Camount> \"\u003Cdescription>\"\n4. IF denied:\n   a. Tell the user what you want to do and why\n   b. Suggest a mandate (show scope, duration, constraints)\n   c. Wait for approval\n   d. If approved, create the mandate, then proceed\n```\n\n### How to Ask for Permission\n\nWhen denied, present it clearly and concisely:\n\n```\nI need to [ACTION] but don't have a mandate for it.\n\n📋 [CATEGORY]: [what you want to do]\n🎯 Target: [specific target]\n⏰ Suggested duration: [reasonable TTL]\n\nWant me to set this up? I can also create a broader mandate if you'd\nprefer (e.g., all emails to @company.com for 30 days).\n```\n\n**DO NOT:**\n- Bypass the check and do it anyway\n- Ask repeatedly for the same thing if denied\n- Create mandates yourself without user approval\n- Pretend you checked when you didn't\n\n**DO:**\n- Suggest templates when appropriate (\"Want me to set up `dev-tools`?\")\n- Batch similar requests (\"I'll need to run several git commands — want a dev-tools mandate?\")\n- Log every action after completion\n- Mention remaining limits when relevant (\"3\u002F20 daily emails used\")\n\n### First-Time Setup\n\nIf `check-action` returns `\"hint\": \"templates\"`, the ledger is empty. Guide the user:\n\n```\nAgent Passport isn't set up yet. It takes 30 seconds:\n\n  mandate-ledger.sh init agent:me \"Your Name\" \"assistant\" \"openclaw\"\n  mandate-ledger.sh create-from-template dev-tools\n\nWant me to run this for you?\n```\n\n### Logging Actions\n\nAfter every authorized action, log it:\n\n```bash\n$SCRIPT_DIR\u002Fmandate-ledger.sh log-action \"\u003Cmandate_id>\" \u003Camount> \"\u003Cdescription>\"\n```\n\n- For financial: amount = dollars spent\n- For everything else: amount = 1\n- Description should be human-readable: \"Sent email to bob@company.com re: Q1 report\"\n\n### Kill Switch Behavior\n\nIf the user engages the kill switch, all operations are frozen until unlocked.\n\n```bash\n.\u002Fmandate-ledger.sh kill \"user requested freeze\"\n.\u002Fmandate-ledger.sh unlock\n```\n\nAgent behavior when kill switch is active:\n- Do not attempt sensitive actions\n- Do not retry `check-action` in a loop\n- Tell user operations are blocked and request explicit `unlock`\n\n---\n\n## Overview\n\nAgent Passport provides a consent layer for agent autonomy. Instead of all-or-nothing permissions, users grant **mandates** with specific constraints:\n\n```\n\"I authorize this agent to [ACTION] with [CONSTRAINTS] until [EXPIRY]\"\n```\n\nThis isn't just about purchases — it's consent-gating for **all sensitive actions**.\n\n## Action Categories\n\n| Category | Examples | Typical Constraints |\n|----------|----------|---------------------|\n| `financial` | Purchases, transfers, subscriptions | Spending cap, merchant allowlist |\n| `communication` | Emails, messages, tweets, posts | Recipient allowlist, rate limit |\n| `data` | Delete files, edit docs, DB writes | Path allowlist, require backup |\n| `system` | Shell commands, installs, configs | Command allowlist, no sudo |\n| `external_api` | Third-party API calls | Service allowlist, rate limit |\n| `identity` | Public actions \"as\" the user | Human review required |\n\n## Wildcard Patterns\n\nAllowlists and deny lists support three wildcard styles:\n\n| Pattern | Matches | Example |\n|---------|---------|---------|\n| `prefix *` | Anything starting with prefix | `git *` → `git pull`, `git status` |\n| `*.suffix` | Anything ending with suffix | `*.env` → `config.env`, `.env` |\n| `*middle*` | Anything containing middle | `*\u002F.git\u002F*` → `repo\u002F.git\u002Fconfig` |\n| `*@domain` | Email domain match | `*@company.com` → `bob@company.com` |\n| `exact` | Exact match only | `api.github.com` |\n\n## Modes\n\n- **Local mode** (default): Mandates stored in `~\u002F.openclaw\u002Fagent-passport\u002F`. Free tier is fully offline. Pro tier makes periodic API calls to `api.agentpassportai.com` for license validation and threat definition updates.\n- **Preview mode:** No storage, no network. Generates validated payloads and curl templates.\n- **Live mode (roadmap):** Future connection to Agent Bridge backend for multi-agent sync and compliance. Not yet implemented.\n\n## Quick Start Commands\n\n```bash\n# Initialize with identity\n.\u002Fmandate-ledger.sh init \u003Cagent_id> \u003Cprincipal> [scope] [provider]\n\n# Templates (auto-detects agent if registered)\n.\u002Fmandate-ledger.sh templates\n.\u002Fmandate-ledger.sh create-from-template dev-tools\n.\u002Fmandate-ledger.sh create-from-template email-team \u003Cdomain>\n.\u002Fmandate-ledger.sh create-from-template file-ops \u003Cpath>\n.\u002Fmandate-ledger.sh create-from-template web-research\n.\u002Fmandate-ledger.sh create-from-template safe-browsing\n.\u002Fmandate-ledger.sh create-from-template coding\n.\u002Fmandate-ledger.sh create-from-template email-assistant\n.\u002Fmandate-ledger.sh create-from-template read-only\n.\u002Fmandate-ledger.sh create-from-template full-auto\n\n# Quick create (human-friendly durations: 7d, 24h, 30m)\n.\u002Fmandate-ledger.sh create-quick \u003Ctype> \u003Cagent_id> \u003Callowlist_csv> \u003Cduration> [amount_cap]\n\n# Check & log\n.\u002Fmandate-ledger.sh check-action \u003Cagent> \u003Ctype> \u003Ctarget> [amount]\n.\u002Fmandate-ledger.sh log-action \u003Cmandate_id> \u003Camount> \"\u003Cdescription>\"\n\n# Audit\n.\u002Fmandate-ledger.sh audit [limit]\n.\u002Fmandate-ledger.sh summary\n\n# Threat definitions\n.\u002Fmandate-ledger.sh init-definitions\n.\u002Fmandate-ledger.sh update-definitions\n.\u002Fmandate-ledger.sh definitions-status\n```\n\n## Commands Reference\n\n### Quick Start\n```bash\ninit [agent_id] [principal] [scope] [provider]\n                           # Initialize ledger, optionally register agent\ntemplates                  # List available templates\ncreate-from-template \u003Ct>   # Create mandate from template\n  [agent_id] [args...]\ncreate-quick \u003Ctype>        # Create with positional args\n  \u003Cagent_id> \u003Callowlist>\n  \u003Cduration> [amount_cap]\n```\n\n### Mandate Lifecycle\n```bash\ncreate \u003Cjson>              # Create mandate (include action_type)\ncreate-with-kya \u003Cjson>     # Create with auto-attached agent KYA\nget \u003Cmandate_id>           # Get mandate by ID\nlist [filter]              # List mandates (all|active|revoked|\u003Caction_type>)\nrevoke \u003Cmandate_id> [why]  # Revoke a mandate\n```\n\n### Authorization\n```bash\ncheck-action \u003Cagent> \u003Ctype> \u003Ctarget> [amount]\n                           # Check if action is authorized\nlog-action \u003Cmandate_id> \u003Camount> [description]\n                           # Log action against mandate\nkill \u003Creason>               # Engage kill switch and freeze execution\nunlock                      # Disengage kill switch\n```\n\n### Audit & Reporting\n```bash\naudit [limit]              # Show recent audit entries\naudit-mandate \u003Cid>         # Show audit for specific mandate\naudit-summary [since]      # Summary by action type\nsummary                    # Show overall ledger stats\nexport                     # Export full ledger as JSON\n```\n\n### Threat Definitions\n```bash\ninit-definitions           # Write bundled threat-definitions.json to LEDGER_DIR\nupdate-definitions         # Refresh definitions (Pro: API pull, Free: bundled copy)\n  [--force] [--offline]\ndefinitions-status         # Show version, pattern counts, and last update\n```\n\n### KYA (Know Your Agent)\n```bash\nkya-register \u003Cagent_id> \u003Cprincipal> \u003Cscope> [provider]\nkya-get \u003Cagent_id>\nkya-list\nkya-revoke \u003Cagent_id> [why]\n```\n\n## Mandate Structure\n\n```json\n{\n  \"mandate_id\": \"mandate_1770412575_3039e369\",\n  \"action_type\": \"communication\",\n  \"agent_id\": \"agent:my-assistant\",\n  \"scope\": {\n    \"allowlist\": [\"*@mycompany.com\", \"bob@partner.com\"],\n    \"deny\": [\"*@competitor.com\"],\n    \"rate_limit\": \"20\u002Fday\",\n    \"kya\": { \"status\": \"verified\", \"verified_principal\": \"Mark\" }\n  },\n  \"amount_cap\": null,\n  \"ttl\": \"2026-02-13T00:00:00Z\",\n  \"status\": \"active\",\n  \"usage\": { \"count\": 5, \"total_amount\": 0 },\n  \"created_at\": \"2026-02-06T22:00:00Z\"\n}\n```\n\n## Agent Bridge (Future Roadmap)\n\n> **Note:** Free tier is fully local with no network calls. Pro tier (`AGENT_PASSPORT_LICENSE_KEY` set) makes periodic HTTPS calls to `api.agentpassportai.com` for license validation and threat definition updates. No usage data or scan results are transmitted. Agent Bridge is a planned future service.\n\nLocal mode handles single-user, single-agent scenarios. A future Agent Bridge service would add:\n\n- **Multi-agent coordination** — prevent overlapping mandates\n- **Cross-device sync** — same mandates everywhere\n- **Organization policies** — IT guardrails, user customization within\n- **Compliance reporting** — audit exports for regulatory needs\n- **Merchant\u002Fservice registry** — verified vendors, trust scores\n\nExport local ledger anytime: `.\u002Fmandate-ledger.sh export > backup.json`\n\n## Configuration (OpenClaw)\n\n```json\n{\n  \"skills\": {\n    \"entries\": {\n      \"agent-passport\": {\n        \"env\": {\n          \"AGENT_PASSPORT_LOCAL_LEDGER\": \"true\"\n        },\n        \"config\": {\n          \"default_currency\": \"USD\",\n          \"default_ttl_minutes\": 60,\n          \"confirm_threshold_amount\": 50\n        }\n      }\n    }\n  }\n}\n```\n\n## Storage\n\nAll data stored locally in `~\u002F.openclaw\u002Fagent-passport\u002F`:\n- `mandates.json` — mandate ledger\n- `agents.json` — KYA registry\n- `audit.json` — action audit trail\n- `threat-definitions.json` — active threat pattern definitions\n- `threat-definitions.bak` — previous definitions backup\n- `.threat-meta.json` — last update\u002Fversion\u002Fsource metadata\n\n## Safety\n\n- Never leak secrets into prompts, logs, or outputs\n- Mandates constrain actions, but don't prevent all misuse\n- Audit trail provides accountability, not prevention\n- Use KYA to verify agent identity before granting broad mandates\n",{"name":5,"version":24,"metadata":25,"description":7,"user-invocable":37},"2.4.0",{"openclaw":26},{"requires":27},{"env":28,"bins":30},[29],"AGENT_PASSPORT_LEDGER_DIR",[31,32,33,34,35,36],"jq","bc","xxd","head","date","mkdir",true,"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fa\u002Fagent-passport",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":37},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agent-passport",{"tool":53,"command":54},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agent-passport",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agent-passport","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fagent-passport\u002FSKILL.md",[],[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":68},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":68},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":68},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":68},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":68},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":68},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]