[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75M7Z184C331K5TYSJS0AEV":3,"skill-same:01M75M7Z184C331K5TYSJS0AEV":71},{"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":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M75M7Z184C331K5TYSJS0AEV","context-verifier",null,"Know the file you're editing is the file you think it is — verify integrity before you act","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fleegitw\u002Fcontext-verifier\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: context-verifier\nversion: 1.5.1\ndescription: Know the file you're editing is the file you think it is — verify integrity before you act\nauthor: Live Neon \u003Ccontact@liveneon.dev>\nhomepage: https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Fcontext-verifier\nrepository: leegitw\u002Fcontext-verifier\nlicense: MIT\ntags: [agentic, verification, integrity, validation, checksums, drift-detection, state, file-verification]\nlayer: foundation\nstatus: active\nalias: cv\nmetadata:\n  openclaw:\n    requires:\n      config:\n        - .openclaw\u002Fcontext-verifier.yaml\n        - .claude\u002Fcontext-verifier.yaml\n      workspace:\n        - output\u002Fcontext-packets\u002F\n---\n\n# context-verifier (検証)\n\nUnified skill for file hash computation, integrity verification, severity tagging,\nand context packet creation. Consolidates 3 granular skills into a single verification system.\n\n**Trigger**: 明示呼出 (explicit invocation)\n\n**Source skills**: context-packet, file-verifier, severity-tagger\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Fcontext-verifier\n```\n\n**Dependencies**: None (foundational skill)\n\n**Standalone usage**: This skill is fully functional standalone. It provides file integrity\nverification that other skills in the suite depend on. Install this first when adopting\nthe Neon Agentic Suite.\n\n**Data handling**: This skill performs local-only operations. Hash computation uses standard\nSHA256 algorithms locally — no file contents are sent to any model, API, or external service.\nResults are written to `output\u002Fcontext-packets\u002F` in your workspace. The skill reads config from\n`.openclaw\u002Fcontext-verifier.yaml` or `.claude\u002Fcontext-verifier.yaml` only.\n\n**File access scope**: This skill reads user-specified files for hash computation. The metadata\ndeclares config and output paths only — the skill will read ANY file path you provide to\n`\u002Fcv hash`, `\u002Fcv verify`, or `\u002Fcv packet`. Use caution with sensitive files.\n\n## What This Solves\n\nAI agents sometimes operate on stale data — editing a file that changed since it was read, or trusting cached content that's now outdated. This skill prevents that by:\n\n1. **Computing hashes** of files before and after operations\n2. **Detecting changes** between read and write\n3. **Generating context packets** with verifiable checksums for review workflows\n\n**The insight**: Trust but verify. The file you read might not be the file you're about to edit. Check first.\n\n## Usage\n\n```\n\u002Fcv \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Fcv hash` | 哈希 | file→SHA256(content) | Explicit |\n| `\u002Fcv verify` | 検証 | file×hash→match✓∨mismatch✗ | Explicit |\n| `\u002Fcv tag` | 標記 | file→severity∈{critical,important,minor} | Explicit |\n| `\u002Fcv packet` | 包装 | files[]→{path,hash,severity,timestamp}[] | Explicit |\n\n## Arguments\n\n### \u002Fcv hash\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File path to hash |\n| --algorithm | No | Hash algorithm: `sha256` only (MD5\u002FSHA-1 removed - cryptographically broken) |\n\n### \u002Fcv verify\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File path to verify |\n| hash | Yes | Expected hash value |\n| --algorithm | No | Hash algorithm: sha256 only |\n\n### \u002Fcv tag\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File path to tag |\n| severity | No | Severity level: `critical`, `important`, `minor` (auto-detected if omitted) |\n\n### \u002Fcv packet\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| files | Yes | Comma-separated file paths or glob pattern |\n| --name | No | Packet name (default: auto-generated) |\n| --include-content | No | Include file content in packet (default: false) - **see Security section** |\n\n> **⚠️ Security Warning**: The `--include-content` flag stores file contents to disk.\n> Never use this flag with sensitive files (`.env`, credentials, secrets).\n> See the [Security Considerations](#security-considerations) section below.\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Fcontext-verifier.yaml` (OpenClaw standard)\n2. `.claude\u002Fcontext-verifier.yaml` (Claude Code compatibility)\n3. Defaults (built-in patterns)\n\n## Security Considerations\n\n**Local-only processing**: All hash computation uses standard SHA256 algorithms executed locally.\nNo file contents are ever sent to any LLM, API, or external service. The \"agent's model\" is only\nused to interpret your commands — not to process file contents.\n\n**What this skill does NOT do:**\n- Send file contents to any model or API (hashing is local)\n- Call external APIs or third-party services\n- Modify source files (only writes to `output\u002Fcontext-packets\u002F`)\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Fcontext-verifier.yaml` and `.claude\u002Fcontext-verifier.yaml`\n- **Any user-specified files** for hash computation (read-only) — the skill reads whatever paths you provide\n- Its own output directory `output\u002Fcontext-packets\u002F` (write)\n\n**⚠️ IMPORTANT**: Unlike other skills in this suite, context-verifier reads arbitrary files that\nyou specify. The metadata only declares config\u002Foutput paths. When you run `\u002Fcv hash myfile.go`,\nthe skill reads `myfile.go` even though it's not in the metadata. This is by design — verification\nrequires reading the files you want to verify.\n\nThis skill handles file metadata and optionally file contents. Follow these guidelines:\n\n### Sensitive File Detection (Not Reading)\n\nThe `critical_patterns` (e.g., `*.env`, `*credentials*`, `*secret*`) are used for:\n- **Detection**: Identifying files that should trigger warnings\n- **Severity tagging**: Marking files as critical for change-blocking behavior\n\nBy default, `\u002Fcv hash` and `\u002Fcv packet` compute hashes **without reading file contents into output**.\nThe hash is computed but the file content is not stored.\n\n### --include-content Flag\n\n**⚠️ WARNING**: The `--include-content` flag writes actual file contents to disk.\n\n| Risk | Mitigation |\n|------|------------|\n| Secrets written to disk | Never use `--include-content` with `.env`, credentials, or secret files |\n| Sensitive data in git | Add `output\u002Fcontext-packets\u002F` to `.gitignore` (see below) |\n| Data retention | Packets are stored indefinitely; manually delete when no longer needed |\n\n**Recommended usage**:\n```bash\n# Safe: Hash only (default) - no content stored\n\u002Fcv packet src\u002F*.go --name \"pre-refactor\"\n\n# Risky: Content included - ensure no sensitive files in glob\n\u002Fcv packet docs\u002F*.md --name \"docs-backup\" --include-content\n\n# NEVER do this:\n\u002Fcv packet .env --include-content  # Stores secrets to disk!\n```\n\n### Required .gitignore Entry\n\nAdd to your `.gitignore` to prevent accidental commits:\n\n```gitignore\n# Context verification packets (may contain sensitive data)\noutput\u002Fcontext-packets\u002F\n```\n\n### Storage and Retention\n\n- **Location**: Packets stored in `output\u002Fcontext-packets\u002F` (workspace-local)\n- **Format**: Unencrypted JSON\n- **Retention**: No automatic deletion; clean up manually\n- **Access**: Standard filesystem permissions (no additional access controls)\n\nFor sensitive environments, consider:\n1. Restricting `output\u002F` directory permissions\n2. Using encrypted filesystems\n3. Periodic cleanup of old packets\n\n### Provenance\n\nThis skill is developed by Live Neon (https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills) and published\nto ClawHub under the `leegitw` account. Both refer to the same maintainer.\n\n## Core Logic\n\n### Hash Computation\n\nDefault algorithm: SHA-256\n\n```\nhash(file) = SHA256(file.content)\n```\n\n### Severity Classification\n\nFiles are auto-classified based on configurable patterns:\n\n| Severity | Default Patterns | Behavior on Change |\n|----------|------------------|-------------------|\n| critical | `*.env`, `*credentials*`, `*secret*`, project config | Block operation |\n| important | `*.go`, `*.ts`, `*.md` (in docs\u002F) | Warn user |\n| minor | `*.log`, `*.tmp`, `output\u002F*` | Info only |\n\nCritical file patterns are configurable via `.openclaw\u002Fcontext-verifier.yaml`:\n\n```yaml\n# .openclaw\u002Fcontext-verifier.yaml\ncritical_patterns:\n  - \"*.env\"\n  - \"*credentials*\"\n  - \"*secret*\"\n  - \"CLAUDE.md\"     # Claude Code projects\n  - \"AGENTS.md\"     # OpenClaw projects\n  - \"pyproject.toml\" # Python projects\n  - \"Cargo.toml\"    # Rust projects\n```\n\n### Context Packet Structure\n\n```json\n{\n  \"id\": \"PKT-20260215-001\",\n  \"created\": \"2026-02-15T10:30:00Z\",\n  \"files\": [\n    {\n      \"path\": \"src\u002Fmain.go\",\n      \"hash\": \"abc123...\",\n      \"severity\": \"important\",\n      \"size\": 1234,\n      \"modified\": \"2026-02-15T10:00:00Z\"\n    }\n  ],\n  \"metadata\": {\n    \"purpose\": \"pre-refactor snapshot\",\n    \"creator\": \"context-verifier\"\n  }\n}\n```\n\n## Output\n\n### \u002Fcv hash output\n\n```\n[HASH] src\u002Fmain.go\nAlgorithm: SHA-256\nHash: a1b2c3d4e5f6...\nSize: 1,234 bytes\nModified: 2026-02-15 10:00:00\n```\n\n### \u002Fcv verify output (match)\n\n```\n[VERIFY] src\u002Fmain.go\nStatus: ✓ MATCH\nExpected: a1b2c3d4e5f6...\nActual:   a1b2c3d4e5f6...\n```\n\n### \u002Fcv verify output (mismatch)\n\n```\n[VERIFY] src\u002Fmain.go\nStatus: ✗ MISMATCH\nExpected: a1b2c3d4e5f6...\nActual:   x9y8z7w6v5u4...\n\nWARNING: File has changed since last read.\nAction: Re-read file before making changes.\n```\n\n### \u002Fcv tag output\n\n```\n[TAG] src\u002Fmain.go\nSeverity: important\nReason: Go source file\nBehavior: Warn on unexpected change\n```\n\n### \u002Fcv packet output\n\n```\n[PACKET CREATED]\nID: PKT-20260215-001\nFiles: 4\nTotal size: 10,234 bytes\n\nFiles included:\n- src\u002Fmain.go (important) - a1b2c3...\n- src\u002Fhandler.go (important) - d4e5f6...\n- docs\u002FREADME.md (important) - j0k1l2...\n- config\u002Fsettings.yaml (important) - m3n4o5...\n\nStored: output\u002Fcontext-packets\u002FPKT-20260215-001.json\n```\n\n> **Note**: Avoid including sensitive files (`.env`, credentials) in packets.\n> Use specific globs like `src\u002F*.go` rather than `*` to exclude secrets.\n\n## Integration\n\n- **Layer**: Foundation (no dependencies)\n- **Depends on**: None (foundational verification system)\n- **Used by**: failure-memory (for file change detection), constraint-engine (for pre-action checks)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| File not found | Error: \"File not found: {path}\" |\n| Permission denied | Error: \"Cannot read file: {path}\" |\n| Invalid hash format | Error: \"Invalid hash format. Expected: {algorithm}\" |\n| Glob matches no files | Warning: \"No files match pattern: {glob}\" |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| Hash mismatch | Alert user, suggest re-read of file |\n| Critical file changed | Block operation, require verification |\n| Packet created | Store in `output\u002Fcontext-packets\u002F` for audit |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\noutput\u002F\n└── context-packets\u002F\n    └── PKT-YYYYMMDD-XXX.json\n```\n\n## Examples\n\n### Verify file before editing\n\n```\n\u002Fcv hash src\u002Fmain.go\n# Save hash: a1b2c3d4e5f6...\n\n# ... later, before editing ...\n\n\u002Fcv verify src\u002Fmain.go a1b2c3d4e5f6\n# ✓ MATCH - safe to edit\n```\n\n### Create context packet for refactoring\n\n```\n\u002Fcv packet src\u002F*.go,internal\u002F**\u002F*.go --name \"pre-refactor\"\n# Creates packet with all Go files\n\n# ... after refactoring ...\n\n# Can compare against packet to see what changed\n```\n\n### Tag sensitive files\n\n```\n\u002Fcv tag .env\n# Severity: critical\n\n\u002Fcv tag src\u002Fhandler.go\n# Severity: important\n```\n\n### Verify database migration before deployment\n\n```\n\u002Fcv packet db\u002Fmigrations\u002F*.sql --name \"pre-deploy-migrations\"\n# Creates packet with all migration files\n\n# After staging deployment...\n\u002Fcv verify db\u002Fmigrations\u002F001_users.sql abc123...\n# ✓ MATCH - migration file unchanged, safe to deploy to production\n```\n\n### Create API schema verification packet\n\n```\n\u002Fcv packet api\u002Fschemas\u002F*.json,api\u002Fopenapi.yaml --name \"api-schema-v2\"\n# Creates packet with all API schema files for version control\n```\n\n## Acceptance Criteria\n\n- [ ] `\u002Fcv hash` computes SHA-256 hash of file\n- [ ] `\u002Fcv verify` compares file hash against expected value\n- [ ] `\u002Fcv verify` clearly indicates match\u002Fmismatch\n- [ ] `\u002Fcv tag` auto-classifies file severity based on patterns\n- [ ] `\u002Fcv tag` allows manual severity override\n- [ ] `\u002Fcv packet` creates JSON packet with file metadata\n- [ ] `\u002Fcv packet` supports glob patterns\n- [ ] Critical file changes trigger block behavior\n- [ ] Workspace files stored in documented location\n\n---\n\n*Consolidated from 3 skills as part of agentic skills consolidation (2026-02-15).*\n","# context-verifier (検証)\n\nUnified skill for file hash computation, integrity verification, severity tagging,\nand context packet creation. Consolidates 3 granular skills into a single verification system.\n\n**Trigger**: 明示呼出 (explicit invocation)\n\n**Source skills**: context-packet, file-verifier, severity-tagger\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Fcontext-verifier\n```\n\n**Dependencies**: None (foundational skill)\n\n**Standalone usage**: This skill is fully functional standalone. It provides file integrity\nverification that other skills in the suite depend on. Install this first when adopting\nthe Neon Agentic Suite.\n\n**Data handling**: This skill performs local-only operations. Hash computation uses standard\nSHA256 algorithms locally — no file contents are sent to any model, API, or external service.\nResults are written to `output\u002Fcontext-packets\u002F` in your workspace. The skill reads config from\n`.openclaw\u002Fcontext-verifier.yaml` or `.claude\u002Fcontext-verifier.yaml` only.\n\n**File access scope**: This skill reads user-specified files for hash computation. The metadata\ndeclares config and output paths only — the skill will read ANY file path you provide to\n`\u002Fcv hash`, `\u002Fcv verify`, or `\u002Fcv packet`. Use caution with sensitive files.\n\n## What This Solves\n\nAI agents sometimes operate on stale data — editing a file that changed since it was read, or trusting cached content that's now outdated. This skill prevents that by:\n\n1. **Computing hashes** of files before and after operations\n2. **Detecting changes** between read and write\n3. **Generating context packets** with verifiable checksums for review workflows\n\n**The insight**: Trust but verify. The file you read might not be the file you're about to edit. Check first.\n\n## Usage\n\n```\n\u002Fcv \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Fcv hash` | 哈希 | file→SHA256(content) | Explicit |\n| `\u002Fcv verify` | 検証 | file×hash→match✓∨mismatch✗ | Explicit |\n| `\u002Fcv tag` | 標記 | file→severity∈{critical,important,minor} | Explicit |\n| `\u002Fcv packet` | 包装 | files[]→{path,hash,severity,timestamp}[] | Explicit |\n\n## Arguments\n\n### \u002Fcv hash\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File path to hash |\n| --algorithm | No | Hash algorithm: `sha256` only (MD5\u002FSHA-1 removed - cryptographically broken) |\n\n### \u002Fcv verify\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File path to verify |\n| hash | Yes | Expected hash value |\n| --algorithm | No | Hash algorithm: sha256 only |\n\n### \u002Fcv tag\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File path to tag |\n| severity | No | Severity level: `critical`, `important`, `minor` (auto-detected if omitted) |\n\n### \u002Fcv packet\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| files | Yes | Comma-separated file paths or glob pattern |\n| --name | No | Packet name (default: auto-generated) |\n| --include-content | No | Include file content in packet (default: false) - **see Security section** |\n\n> **⚠️ Security Warning**: The `--include-content` flag stores file contents to disk.\n> Never use this flag with sensitive files (`.env`, credentials, secrets).\n> See the [Security Considerations](#security-considerations) section below.\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Fcontext-verifier.yaml` (OpenClaw standard)\n2. `.claude\u002Fcontext-verifier.yaml` (Claude Code compatibility)\n3. Defaults (built-in patterns)\n\n## Security Considerations\n\n**Local-only processing**: All hash computation uses standard SHA256 algorithms executed locally.\nNo file contents are ever sent to any LLM, API, or external service. The \"agent's model\" is only\nused to interpret your commands — not to process file contents.\n\n**What this skill does NOT do:**\n- Send file contents to any model or API (hashing is local)\n- Call external APIs or third-party services\n- Modify source files (only writes to `output\u002Fcontext-packets\u002F`)\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Fcontext-verifier.yaml` and `.claude\u002Fcontext-verifier.yaml`\n- **Any user-specified files** for hash computation (read-only) — the skill reads whatever paths you provide\n- Its own output directory `output\u002Fcontext-packets\u002F` (write)\n\n**⚠️ IMPORTANT**: Unlike other skills in this suite, context-verifier reads arbitrary files that\nyou specify. The metadata only declares config\u002Foutput paths. When you run `\u002Fcv hash myfile.go`,\nthe skill reads `myfile.go` even though it's not in the metadata. This is by design — verification\nrequires reading the files you want to verify.\n\nThis skill handles file metadata and optionally file contents. Follow these guidelines:\n\n### Sensitive File Detection (Not Reading)\n\nThe `critical_patterns` (e.g., `*.env`, `*credentials*`, `*secret*`) are used for:\n- **Detection**: Identifying files that should trigger warnings\n- **Severity tagging**: Marking files as critical for change-blocking behavior\n\nBy default, `\u002Fcv hash` and `\u002Fcv packet` compute hashes **without reading file contents into output**.\nThe hash is computed but the file content is not stored.\n\n### --include-content Flag\n\n**⚠️ WARNING**: The `--include-content` flag writes actual file contents to disk.\n\n| Risk | Mitigation |\n|------|------------|\n| Secrets written to disk | Never use `--include-content` with `.env`, credentials, or secret files |\n| Sensitive data in git | Add `output\u002Fcontext-packets\u002F` to `.gitignore` (see below) |\n| Data retention | Packets are stored indefinitely; manually delete when no longer needed |\n\n**Recommended usage**:\n```bash\n# Safe: Hash only (default) - no content stored\n\u002Fcv packet src\u002F*.go --name \"pre-refactor\"\n\n# Risky: Content included - ensure no sensitive files in glob\n\u002Fcv packet docs\u002F*.md --name \"docs-backup\" --include-content\n\n# NEVER do this:\n\u002Fcv packet .env --include-content  # Stores secrets to disk!\n```\n\n### Required .gitignore Entry\n\nAdd to your `.gitignore` to prevent accidental commits:\n\n```gitignore\n# Context verification packets (may contain sensitive data)\noutput\u002Fcontext-packets\u002F\n```\n\n### Storage and Retention\n\n- **Location**: Packets stored in `output\u002Fcontext-packets\u002F` (workspace-local)\n- **Format**: Unencrypted JSON\n- **Retention**: No automatic deletion; clean up manually\n- **Access**: Standard filesystem permissions (no additional access controls)\n\nFor sensitive environments, consider:\n1. Restricting `output\u002F` directory permissions\n2. Using encrypted filesystems\n3. Periodic cleanup of old packets\n\n### Provenance\n\nThis skill is developed by Live Neon (https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills) and published\nto ClawHub under the `leegitw` account. Both refer to the same maintainer.\n\n## Core Logic\n\n### Hash Computation\n\nDefault algorithm: SHA-256\n\n```\nhash(file) = SHA256(file.content)\n```\n\n### Severity Classification\n\nFiles are auto-classified based on configurable patterns:\n\n| Severity | Default Patterns | Behavior on Change |\n|----------|------------------|-------------------|\n| critical | `*.env`, `*credentials*`, `*secret*`, project config | Block operation |\n| important | `*.go`, `*.ts`, `*.md` (in docs\u002F) | Warn user |\n| minor | `*.log`, `*.tmp`, `output\u002F*` | Info only |\n\nCritical file patterns are configurable via `.openclaw\u002Fcontext-verifier.yaml`:\n\n```yaml\n# .openclaw\u002Fcontext-verifier.yaml\ncritical_patterns:\n  - \"*.env\"\n  - \"*credentials*\"\n  - \"*secret*\"\n  - \"CLAUDE.md\"     # Claude Code projects\n  - \"AGENTS.md\"     # OpenClaw projects\n  - \"pyproject.toml\" # Python projects\n  - \"Cargo.toml\"    # Rust projects\n```\n\n### Context Packet Structure\n\n```json\n{\n  \"id\": \"PKT-20260215-001\",\n  \"created\": \"2026-02-15T10:30:00Z\",\n  \"files\": [\n    {\n      \"path\": \"src\u002Fmain.go\",\n      \"hash\": \"abc123...\",\n      \"severity\": \"important\",\n      \"size\": 1234,\n      \"modified\": \"2026-02-15T10:00:00Z\"\n    }\n  ],\n  \"metadata\": {\n    \"purpose\": \"pre-refactor snapshot\",\n    \"creator\": \"context-verifier\"\n  }\n}\n```\n\n## Output\n\n### \u002Fcv hash output\n\n```\n[HASH] src\u002Fmain.go\nAlgorithm: SHA-256\nHash: a1b2c3d4e5f6...\nSize: 1,234 bytes\nModified: 2026-02-15 10:00:00\n```\n\n### \u002Fcv verify output (match)\n\n```\n[VERIFY] src\u002Fmain.go\nStatus: ✓ MATCH\nExpected: a1b2c3d4e5f6...\nActual:   a1b2c3d4e5f6...\n```\n\n### \u002Fcv verify output (mismatch)\n\n```\n[VERIFY] src\u002Fmain.go\nStatus: ✗ MISMATCH\nExpected: a1b2c3d4e5f6...\nActual:   x9y8z7w6v5u4...\n\nWARNING: File has changed since last read.\nAction: Re-read file before making changes.\n```\n\n### \u002Fcv tag output\n\n```\n[TAG] src\u002Fmain.go\nSeverity: important\nReason: Go source file\nBehavior: Warn on unexpected change\n```\n\n### \u002Fcv packet output\n\n```\n[PACKET CREATED]\nID: PKT-20260215-001\nFiles: 4\nTotal size: 10,234 bytes\n\nFiles included:\n- src\u002Fmain.go (important) - a1b2c3...\n- src\u002Fhandler.go (important) - d4e5f6...\n- docs\u002FREADME.md (important) - j0k1l2...\n- config\u002Fsettings.yaml (important) - m3n4o5...\n\nStored: output\u002Fcontext-packets\u002FPKT-20260215-001.json\n```\n\n> **Note**: Avoid including sensitive files (`.env`, credentials) in packets.\n> Use specific globs like `src\u002F*.go` rather than `*` to exclude secrets.\n\n## Integration\n\n- **Layer**: Foundation (no dependencies)\n- **Depends on**: None (foundational verification system)\n- **Used by**: failure-memory (for file change detection), constraint-engine (for pre-action checks)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| File not found | Error: \"File not found: {path}\" |\n| Permission denied | Error: \"Cannot read file: {path}\" |\n| Invalid hash format | Error: \"Invalid hash format. Expected: {algorithm}\" |\n| Glob matches no files | Warning: \"No files match pattern: {glob}\" |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| Hash mismatch | Alert user, suggest re-read of file |\n| Critical file changed | Block operation, require verification |\n| Packet created | Store in `output\u002Fcontext-packets\u002F` for audit |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\noutput\u002F\n└── context-packets\u002F\n    └── PKT-YYYYMMDD-XXX.json\n```\n\n## Examples\n\n### Verify file before editing\n\n```\n\u002Fcv hash src\u002Fmain.go\n# Save hash: a1b2c3d4e5f6...\n\n# ... later, before editing ...\n\n\u002Fcv verify src\u002Fmain.go a1b2c3d4e5f6\n# ✓ MATCH - safe to edit\n```\n\n### Create context packet for refactoring\n\n```\n\u002Fcv packet src\u002F*.go,internal\u002F**\u002F*.go --name \"pre-refactor\"\n# Creates packet with all Go files\n\n# ... after refactoring ...\n\n# Can compare against packet to see what changed\n```\n\n### Tag sensitive files\n\n```\n\u002Fcv tag .env\n# Severity: critical\n\n\u002Fcv tag src\u002Fhandler.go\n# Severity: important\n```\n\n### Verify database migration before deployment\n\n```\n\u002Fcv packet db\u002Fmigrations\u002F*.sql --name \"pre-deploy-migrations\"\n# Creates packet with all migration files\n\n# After staging deployment...\n\u002Fcv verify db\u002Fmigrations\u002F001_users.sql abc123...\n# ✓ MATCH - migration file unchanged, safe to deploy to production\n```\n\n### Create API schema verification packet\n\n```\n\u002Fcv packet api\u002Fschemas\u002F*.json,api\u002Fopenapi.yaml --name \"api-schema-v2\"\n# Creates packet with all API schema files for version control\n```\n\n## Acceptance Criteria\n\n- [ ] `\u002Fcv hash` computes SHA-256 hash of file\n- [ ] `\u002Fcv verify` compares file hash against expected value\n- [ ] `\u002Fcv verify` clearly indicates match\u002Fmismatch\n- [ ] `\u002Fcv tag` auto-classifies file severity based on patterns\n- [ ] `\u002Fcv tag` allows manual severity override\n- [ ] `\u002Fcv packet` creates JSON packet with file metadata\n- [ ] `\u002Fcv packet` supports glob patterns\n- [ ] Critical file changes trigger block behavior\n- [ ] Workspace files stored in documented location\n\n---\n\n*Consolidated from 3 skills as part of agentic skills consolidation (2026-02-15).*\n",{"name":5,"tags":24,"alias":33,"layer":34,"author":35,"status":36,"license":15,"version":37,"homepage":38,"metadata":39,"repository":47,"description":7},[25,26,27,28,29,30,31,32],"agentic","verification","integrity","validation","checksums","drift-detection","state","file-verification","cv","foundation","Live Neon \u003Ccontact@liveneon.dev>","active","1.5.1","https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Fcontext-verifier",{"openclaw":40},{"requires":41},{"config":42,"workspace":45},[43,44],".openclaw\u002Fcontext-verifier.yaml",".claude\u002Fcontext-verifier.yaml",[46],"output\u002Fcontext-packets\u002F","leegitw\u002Fcontext-verifier","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fleegitw\u002Fcontext-verifier",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill context-verifier",{"tool":63,"command":64},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill context-verifier",{"tool":66,"command":67},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill context-verifier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fleegitw\u002Fcontext-verifier\u002FSKILL.md",true,[],[72,80,87,94,101,108],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":79},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":79},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":79},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":79},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":79},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]