{
  "schemaVersion": "1.0",
  "item": {
    "slug": "context-verifier",
    "name": "Context Verifier",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/leegitw/context-verifier",
    "canonicalUrl": "https://clawhub.ai/leegitw/context-verifier",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/context-verifier",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-verifier",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/context-verifier"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/context-verifier",
    "agentPageUrl": "https://openagent3.xyz/skills/context-verifier/agent",
    "manifestUrl": "https://openagent3.xyz/skills/context-verifier/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/context-verifier/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "context-verifier (検証)",
        "body": "Unified skill for file hash computation, integrity verification, severity tagging,\nand context packet creation. Consolidates 3 granular skills into a single verification system.\n\nTrigger: 明示呼出 (explicit invocation)\n\nSource skills: context-packet, file-verifier, severity-tagger"
      },
      {
        "title": "Installation",
        "body": "openclaw install leegitw/context-verifier\n\nDependencies: None (foundational skill)\n\nStandalone 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\nData 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/context-packets/ in your workspace. The skill reads config from\n.openclaw/context-verifier.yaml or .claude/context-verifier.yaml only.\n\nFile 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/cv hash, /cv verify, or /cv packet. Use caution with sensitive files."
      },
      {
        "title": "What This Solves",
        "body": "AI 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\nComputing hashes of files before and after operations\nDetecting changes between read and write\nGenerating context packets with verifiable checksums for review workflows\n\nThe insight: Trust but verify. The file you read might not be the file you're about to edit. Check first."
      },
      {
        "title": "Usage",
        "body": "/cv <sub-command> [arguments]"
      },
      {
        "title": "Sub-Commands",
        "body": "CommandCJKLogicTrigger/cv hash哈希file→SHA256(content)Explicit/cv verify検証file×hash→match✓∨mismatch✗Explicit/cv tag標記file→severity∈{critical,important,minor}Explicit/cv packet包装files[]→{path,hash,severity,timestamp}[]Explicit"
      },
      {
        "title": "/cv hash",
        "body": "ArgumentRequiredDescriptionfileYesFile path to hash--algorithmNoHash algorithm: sha256 only (MD5/SHA-1 removed - cryptographically broken)"
      },
      {
        "title": "/cv verify",
        "body": "ArgumentRequiredDescriptionfileYesFile path to verifyhashYesExpected hash value--algorithmNoHash algorithm: sha256 only"
      },
      {
        "title": "/cv tag",
        "body": "ArgumentRequiredDescriptionfileYesFile path to tagseverityNoSeverity level: critical, important, minor (auto-detected if omitted)"
      },
      {
        "title": "/cv packet",
        "body": "ArgumentRequiredDescriptionfilesYesComma-separated file paths or glob pattern--nameNoPacket name (default: auto-generated)--include-contentNoInclude file content in packet (default: false) - see Security section\n\n⚠️ Security Warning: The --include-content flag stores file contents to disk.\nNever use this flag with sensitive files (.env, credentials, secrets).\nSee the Security Considerations section below."
      },
      {
        "title": "Configuration",
        "body": "Configuration is loaded from (in order of precedence):\n\n.openclaw/context-verifier.yaml (OpenClaw standard)\n.claude/context-verifier.yaml (Claude Code compatibility)\nDefaults (built-in patterns)"
      },
      {
        "title": "Security Considerations",
        "body": "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\nWhat this skill does NOT do:\n\nSend file contents to any model or API (hashing is local)\nCall external APIs or third-party services\nModify source files (only writes to output/context-packets/)\n\nWhat this skill accesses:\n\nConfiguration files in .openclaw/context-verifier.yaml and .claude/context-verifier.yaml\nAny user-specified files for hash computation (read-only) — the skill reads whatever paths you provide\nIts own output directory output/context-packets/ (write)\n\n⚠️ IMPORTANT: Unlike other skills in this suite, context-verifier reads arbitrary files that\nyou specify. The metadata only declares config/output paths. When you run /cv 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:"
      },
      {
        "title": "Sensitive File Detection (Not Reading)",
        "body": "The critical_patterns (e.g., *.env, *credentials*, *secret*) are used for:\n\nDetection: Identifying files that should trigger warnings\nSeverity tagging: Marking files as critical for change-blocking behavior\n\nBy default, /cv hash and /cv packet compute hashes without reading file contents into output.\nThe hash is computed but the file content is not stored."
      },
      {
        "title": "--include-content Flag",
        "body": "⚠️ WARNING: The --include-content flag writes actual file contents to disk.\n\nRiskMitigationSecrets written to diskNever use --include-content with .env, credentials, or secret filesSensitive data in gitAdd output/context-packets/ to .gitignore (see below)Data retentionPackets are stored indefinitely; manually delete when no longer needed\n\nRecommended usage:\n\n# Safe: Hash only (default) - no content stored\n/cv packet src/*.go --name \"pre-refactor\"\n\n# Risky: Content included - ensure no sensitive files in glob\n/cv packet docs/*.md --name \"docs-backup\" --include-content\n\n# NEVER do this:\n/cv packet .env --include-content  # Stores secrets to disk!"
      },
      {
        "title": "Required .gitignore Entry",
        "body": "Add to your .gitignore to prevent accidental commits:\n\n# Context verification packets (may contain sensitive data)\noutput/context-packets/"
      },
      {
        "title": "Storage and Retention",
        "body": "Location: Packets stored in output/context-packets/ (workspace-local)\nFormat: Unencrypted JSON\nRetention: No automatic deletion; clean up manually\nAccess: Standard filesystem permissions (no additional access controls)\n\nFor sensitive environments, consider:\n\nRestricting output/ directory permissions\nUsing encrypted filesystems\nPeriodic cleanup of old packets"
      },
      {
        "title": "Provenance",
        "body": "This skill is developed by Live Neon (https://github.com/live-neon/skills) and published\nto ClawHub under the leegitw account. Both refer to the same maintainer."
      },
      {
        "title": "Hash Computation",
        "body": "Default algorithm: SHA-256\n\nhash(file) = SHA256(file.content)"
      },
      {
        "title": "Severity Classification",
        "body": "Files are auto-classified based on configurable patterns:\n\nSeverityDefault PatternsBehavior on Changecritical*.env, *credentials*, *secret*, project configBlock operationimportant*.go, *.ts, *.md (in docs/)Warn userminor*.log, *.tmp, output/*Info only\n\nCritical file patterns are configurable via .openclaw/context-verifier.yaml:\n\n# .openclaw/context-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"
      },
      {
        "title": "Context Packet Structure",
        "body": "{\n  \"id\": \"PKT-20260215-001\",\n  \"created\": \"2026-02-15T10:30:00Z\",\n  \"files\": [\n    {\n      \"path\": \"src/main.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}"
      },
      {
        "title": "/cv hash output",
        "body": "[HASH] src/main.go\nAlgorithm: SHA-256\nHash: a1b2c3d4e5f6...\nSize: 1,234 bytes\nModified: 2026-02-15 10:00:00"
      },
      {
        "title": "/cv verify output (match)",
        "body": "[VERIFY] src/main.go\nStatus: ✓ MATCH\nExpected: a1b2c3d4e5f6...\nActual:   a1b2c3d4e5f6..."
      },
      {
        "title": "/cv verify output (mismatch)",
        "body": "[VERIFY] src/main.go\nStatus: ✗ MISMATCH\nExpected: a1b2c3d4e5f6...\nActual:   x9y8z7w6v5u4...\n\nWARNING: File has changed since last read.\nAction: Re-read file before making changes."
      },
      {
        "title": "/cv tag output",
        "body": "[TAG] src/main.go\nSeverity: important\nReason: Go source file\nBehavior: Warn on unexpected change"
      },
      {
        "title": "/cv packet output",
        "body": "[PACKET CREATED]\nID: PKT-20260215-001\nFiles: 4\nTotal size: 10,234 bytes\n\nFiles included:\n- src/main.go (important) - a1b2c3...\n- src/handler.go (important) - d4e5f6...\n- docs/README.md (important) - j0k1l2...\n- config/settings.yaml (important) - m3n4o5...\n\nStored: output/context-packets/PKT-20260215-001.json\n\nNote: Avoid including sensitive files (.env, credentials) in packets.\nUse specific globs like src/*.go rather than * to exclude secrets."
      },
      {
        "title": "Integration",
        "body": "Layer: Foundation (no dependencies)\nDepends on: None (foundational verification system)\nUsed by: failure-memory (for file change detection), constraint-engine (for pre-action checks)"
      },
      {
        "title": "Failure Modes",
        "body": "ConditionBehaviorFile not foundError: \"File not found: {path}\"Permission deniedError: \"Cannot read file: {path}\"Invalid hash formatError: \"Invalid hash format. Expected: {algorithm}\"Glob matches no filesWarning: \"No files match pattern: {glob}\""
      },
      {
        "title": "Next Steps",
        "body": "After invoking this skill:\n\nConditionActionHash mismatchAlert user, suggest re-read of fileCritical file changedBlock operation, require verificationPacket createdStore in output/context-packets/ for audit"
      },
      {
        "title": "Workspace Files",
        "body": "This skill reads/writes:\n\noutput/\n└── context-packets/\n    └── PKT-YYYYMMDD-XXX.json"
      },
      {
        "title": "Verify file before editing",
        "body": "/cv hash src/main.go\n# Save hash: a1b2c3d4e5f6...\n\n# ... later, before editing ...\n\n/cv verify src/main.go a1b2c3d4e5f6\n# ✓ MATCH - safe to edit"
      },
      {
        "title": "Create context packet for refactoring",
        "body": "/cv packet src/*.go,internal/**/*.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"
      },
      {
        "title": "Tag sensitive files",
        "body": "/cv tag .env\n# Severity: critical\n\n/cv tag src/handler.go\n# Severity: important"
      },
      {
        "title": "Verify database migration before deployment",
        "body": "/cv packet db/migrations/*.sql --name \"pre-deploy-migrations\"\n# Creates packet with all migration files\n\n# After staging deployment...\n/cv verify db/migrations/001_users.sql abc123...\n# ✓ MATCH - migration file unchanged, safe to deploy to production"
      },
      {
        "title": "Create API schema verification packet",
        "body": "/cv packet api/schemas/*.json,api/openapi.yaml --name \"api-schema-v2\"\n# Creates packet with all API schema files for version control"
      },
      {
        "title": "Acceptance Criteria",
        "body": "/cv hash computes SHA-256 hash of file\n /cv verify compares file hash against expected value\n /cv verify clearly indicates match/mismatch\n /cv tag auto-classifies file severity based on patterns\n /cv tag allows manual severity override\n /cv packet creates JSON packet with file metadata\n /cv packet supports glob patterns\n Critical file changes trigger block behavior\n Workspace files stored in documented location\n\nConsolidated from 3 skills as part of agentic skills consolidation (2026-02-15)."
      }
    ],
    "body": "context-verifier (検証)\n\nUnified skill for file hash computation, integrity verification, severity tagging, and context packet creation. Consolidates 3 granular skills into a single verification system.\n\nTrigger: 明示呼出 (explicit invocation)\n\nSource skills: context-packet, file-verifier, severity-tagger\n\nInstallation\nopenclaw install leegitw/context-verifier\n\n\nDependencies: None (foundational skill)\n\nStandalone usage: This skill is fully functional standalone. It provides file integrity verification that other skills in the suite depend on. Install this first when adopting the Neon Agentic Suite.\n\nData handling: This skill performs local-only operations. Hash computation uses standard SHA256 algorithms locally — no file contents are sent to any model, API, or external service. Results are written to output/context-packets/ in your workspace. The skill reads config from .openclaw/context-verifier.yaml or .claude/context-verifier.yaml only.\n\nFile access scope: This skill reads user-specified files for hash computation. The metadata declares config and output paths only — the skill will read ANY file path you provide to /cv hash, /cv verify, or /cv packet. Use caution with sensitive files.\n\nWhat 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\nComputing hashes of files before and after operations\nDetecting changes between read and write\nGenerating context packets with verifiable checksums for review workflows\n\nThe insight: Trust but verify. The file you read might not be the file you're about to edit. Check first.\n\nUsage\n/cv <sub-command> [arguments]\n\nSub-Commands\nCommand\tCJK\tLogic\tTrigger\n/cv hash\t哈希\tfile→SHA256(content)\tExplicit\n/cv verify\t検証\tfile×hash→match✓∨mismatch✗\tExplicit\n/cv tag\t標記\tfile→severity∈{critical,important,minor}\tExplicit\n/cv packet\t包装\tfiles[]→{path,hash,severity,timestamp}[]\tExplicit\nArguments\n/cv hash\nArgument\tRequired\tDescription\nfile\tYes\tFile path to hash\n--algorithm\tNo\tHash algorithm: sha256 only (MD5/SHA-1 removed - cryptographically broken)\n/cv verify\nArgument\tRequired\tDescription\nfile\tYes\tFile path to verify\nhash\tYes\tExpected hash value\n--algorithm\tNo\tHash algorithm: sha256 only\n/cv tag\nArgument\tRequired\tDescription\nfile\tYes\tFile path to tag\nseverity\tNo\tSeverity level: critical, important, minor (auto-detected if omitted)\n/cv packet\nArgument\tRequired\tDescription\nfiles\tYes\tComma-separated file paths or glob pattern\n--name\tNo\tPacket name (default: auto-generated)\n--include-content\tNo\tInclude file content in packet (default: false) - see Security section\n\n⚠️ Security Warning: The --include-content flag stores file contents to disk. Never use this flag with sensitive files (.env, credentials, secrets). See the Security Considerations section below.\n\nConfiguration\n\nConfiguration is loaded from (in order of precedence):\n\n.openclaw/context-verifier.yaml (OpenClaw standard)\n.claude/context-verifier.yaml (Claude Code compatibility)\nDefaults (built-in patterns)\nSecurity Considerations\n\nLocal-only processing: All hash computation uses standard SHA256 algorithms executed locally. No file contents are ever sent to any LLM, API, or external service. The \"agent's model\" is only used to interpret your commands — not to process file contents.\n\nWhat this skill does NOT do:\n\nSend file contents to any model or API (hashing is local)\nCall external APIs or third-party services\nModify source files (only writes to output/context-packets/)\n\nWhat this skill accesses:\n\nConfiguration files in .openclaw/context-verifier.yaml and .claude/context-verifier.yaml\nAny user-specified files for hash computation (read-only) — the skill reads whatever paths you provide\nIts own output directory output/context-packets/ (write)\n\n⚠️ IMPORTANT: Unlike other skills in this suite, context-verifier reads arbitrary files that you specify. The metadata only declares config/output paths. When you run /cv hash myfile.go, the skill reads myfile.go even though it's not in the metadata. This is by design — verification requires reading the files you want to verify.\n\nThis skill handles file metadata and optionally file contents. Follow these guidelines:\n\nSensitive File Detection (Not Reading)\n\nThe critical_patterns (e.g., *.env, *credentials*, *secret*) are used for:\n\nDetection: Identifying files that should trigger warnings\nSeverity tagging: Marking files as critical for change-blocking behavior\n\nBy default, /cv hash and /cv packet compute hashes without reading file contents into output. The 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\nRisk\tMitigation\nSecrets written to disk\tNever use --include-content with .env, credentials, or secret files\nSensitive data in git\tAdd output/context-packets/ to .gitignore (see below)\nData retention\tPackets are stored indefinitely; manually delete when no longer needed\n\nRecommended usage:\n\n# Safe: Hash only (default) - no content stored\n/cv packet src/*.go --name \"pre-refactor\"\n\n# Risky: Content included - ensure no sensitive files in glob\n/cv packet docs/*.md --name \"docs-backup\" --include-content\n\n# NEVER do this:\n/cv packet .env --include-content  # Stores secrets to disk!\n\nRequired .gitignore Entry\n\nAdd to your .gitignore to prevent accidental commits:\n\n# Context verification packets (may contain sensitive data)\noutput/context-packets/\n\nStorage and Retention\nLocation: Packets stored in output/context-packets/ (workspace-local)\nFormat: Unencrypted JSON\nRetention: No automatic deletion; clean up manually\nAccess: Standard filesystem permissions (no additional access controls)\n\nFor sensitive environments, consider:\n\nRestricting output/ directory permissions\nUsing encrypted filesystems\nPeriodic cleanup of old packets\nProvenance\n\nThis skill is developed by Live Neon (https://github.com/live-neon/skills) and published to ClawHub under the leegitw account. Both refer to the same maintainer.\n\nCore Logic\nHash Computation\n\nDefault algorithm: SHA-256\n\nhash(file) = SHA256(file.content)\n\nSeverity Classification\n\nFiles are auto-classified based on configurable patterns:\n\nSeverity\tDefault Patterns\tBehavior on Change\ncritical\t*.env, *credentials*, *secret*, project config\tBlock operation\nimportant\t*.go, *.ts, *.md (in docs/)\tWarn user\nminor\t*.log, *.tmp, output/*\tInfo only\n\nCritical file patterns are configurable via .openclaw/context-verifier.yaml:\n\n# .openclaw/context-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\nContext Packet Structure\n{\n  \"id\": \"PKT-20260215-001\",\n  \"created\": \"2026-02-15T10:30:00Z\",\n  \"files\": [\n    {\n      \"path\": \"src/main.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\nOutput\n/cv hash output\n[HASH] src/main.go\nAlgorithm: SHA-256\nHash: a1b2c3d4e5f6...\nSize: 1,234 bytes\nModified: 2026-02-15 10:00:00\n\n/cv verify output (match)\n[VERIFY] src/main.go\nStatus: ✓ MATCH\nExpected: a1b2c3d4e5f6...\nActual:   a1b2c3d4e5f6...\n\n/cv verify output (mismatch)\n[VERIFY] src/main.go\nStatus: ✗ MISMATCH\nExpected: a1b2c3d4e5f6...\nActual:   x9y8z7w6v5u4...\n\nWARNING: File has changed since last read.\nAction: Re-read file before making changes.\n\n/cv tag output\n[TAG] src/main.go\nSeverity: important\nReason: Go source file\nBehavior: Warn on unexpected change\n\n/cv packet output\n[PACKET CREATED]\nID: PKT-20260215-001\nFiles: 4\nTotal size: 10,234 bytes\n\nFiles included:\n- src/main.go (important) - a1b2c3...\n- src/handler.go (important) - d4e5f6...\n- docs/README.md (important) - j0k1l2...\n- config/settings.yaml (important) - m3n4o5...\n\nStored: output/context-packets/PKT-20260215-001.json\n\n\nNote: Avoid including sensitive files (.env, credentials) in packets. Use specific globs like src/*.go rather than * to exclude secrets.\n\nIntegration\nLayer: Foundation (no dependencies)\nDepends on: None (foundational verification system)\nUsed by: failure-memory (for file change detection), constraint-engine (for pre-action checks)\nFailure Modes\nCondition\tBehavior\nFile not found\tError: \"File not found: {path}\"\nPermission denied\tError: \"Cannot read file: {path}\"\nInvalid hash format\tError: \"Invalid hash format. Expected: {algorithm}\"\nGlob matches no files\tWarning: \"No files match pattern: {glob}\"\nNext Steps\n\nAfter invoking this skill:\n\nCondition\tAction\nHash mismatch\tAlert user, suggest re-read of file\nCritical file changed\tBlock operation, require verification\nPacket created\tStore in output/context-packets/ for audit\nWorkspace Files\n\nThis skill reads/writes:\n\noutput/\n└── context-packets/\n    └── PKT-YYYYMMDD-XXX.json\n\nExamples\nVerify file before editing\n/cv hash src/main.go\n# Save hash: a1b2c3d4e5f6...\n\n# ... later, before editing ...\n\n/cv verify src/main.go a1b2c3d4e5f6\n# ✓ MATCH - safe to edit\n\nCreate context packet for refactoring\n/cv packet src/*.go,internal/**/*.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\nTag sensitive files\n/cv tag .env\n# Severity: critical\n\n/cv tag src/handler.go\n# Severity: important\n\nVerify database migration before deployment\n/cv packet db/migrations/*.sql --name \"pre-deploy-migrations\"\n# Creates packet with all migration files\n\n# After staging deployment...\n/cv verify db/migrations/001_users.sql abc123...\n# ✓ MATCH - migration file unchanged, safe to deploy to production\n\nCreate API schema verification packet\n/cv packet api/schemas/*.json,api/openapi.yaml --name \"api-schema-v2\"\n# Creates packet with all API schema files for version control\n\nAcceptance Criteria\n /cv hash computes SHA-256 hash of file\n /cv verify compares file hash against expected value\n /cv verify clearly indicates match/mismatch\n /cv tag auto-classifies file severity based on patterns\n /cv tag allows manual severity override\n /cv packet creates JSON packet with file metadata\n /cv packet supports glob patterns\n Critical file changes trigger block behavior\n Workspace files stored in documented location\n\nConsolidated from 3 skills as part of agentic skills consolidation (2026-02-15)."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/leegitw/context-verifier",
    "publisherUrl": "https://clawhub.ai/leegitw/context-verifier",
    "owner": "leegitw",
    "version": "1.5.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/context-verifier",
    "downloadUrl": "https://openagent3.xyz/downloads/context-verifier",
    "agentUrl": "https://openagent3.xyz/skills/context-verifier/agent",
    "manifestUrl": "https://openagent3.xyz/skills/context-verifier/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/context-verifier/agent.md"
  }
}