# Send Context Verifier to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/context-verifier", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-verifier", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "context-verifier", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T18:48:42.512Z", "expiresAt": "2026-05-07T18:48:42.512Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-verifier", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=context-verifier", "contentDisposition": "attachment; filename=\"context-verifier-1.5.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "context-verifier" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "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." ] } }, "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" } } ``` ## Documentation ### context-verifier (検証) Unified skill for file hash computation, integrity verification, severity tagging, and context packet creation. Consolidates 3 granular skills into a single verification system. Trigger: 明示呼出 (explicit invocation) Source skills: context-packet, file-verifier, severity-tagger ### Installation openclaw install leegitw/context-verifier Dependencies: None (foundational skill) Standalone 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. Data 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. File 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. ### What This Solves 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: Computing hashes of files before and after operations Detecting changes between read and write Generating context packets with verifiable checksums for review workflows The insight: Trust but verify. The file you read might not be the file you're about to edit. Check first. ### Usage /cv [arguments] ### Sub-Commands 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 ### /cv hash ArgumentRequiredDescriptionfileYesFile path to hash--algorithmNoHash algorithm: sha256 only (MD5/SHA-1 removed - cryptographically broken) ### /cv verify ArgumentRequiredDescriptionfileYesFile path to verifyhashYesExpected hash value--algorithmNoHash algorithm: sha256 only ### /cv tag ArgumentRequiredDescriptionfileYesFile path to tagseverityNoSeverity level: critical, important, minor (auto-detected if omitted) ### /cv packet ArgumentRequiredDescriptionfilesYesComma-separated file paths or glob pattern--nameNoPacket name (default: auto-generated)--include-contentNoInclude file content in packet (default: false) - see Security section ⚠️ 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. ### Configuration Configuration is loaded from (in order of precedence): .openclaw/context-verifier.yaml (OpenClaw standard) .claude/context-verifier.yaml (Claude Code compatibility) Defaults (built-in patterns) ### Security Considerations Local-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. What this skill does NOT do: Send file contents to any model or API (hashing is local) Call external APIs or third-party services Modify source files (only writes to output/context-packets/) What this skill accesses: Configuration files in .openclaw/context-verifier.yaml and .claude/context-verifier.yaml Any user-specified files for hash computation (read-only) — the skill reads whatever paths you provide Its own output directory output/context-packets/ (write) ⚠️ 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. This skill handles file metadata and optionally file contents. Follow these guidelines: ### Sensitive File Detection (Not Reading) The critical_patterns (e.g., *.env, *credentials*, *secret*) are used for: Detection: Identifying files that should trigger warnings Severity tagging: Marking files as critical for change-blocking behavior By 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. ### --include-content Flag ⚠️ WARNING: The --include-content flag writes actual file contents to disk. RiskMitigationSecrets 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 Recommended usage: # Safe: Hash only (default) - no content stored /cv packet src/*.go --name "pre-refactor" # Risky: Content included - ensure no sensitive files in glob /cv packet docs/*.md --name "docs-backup" --include-content # NEVER do this: /cv packet .env --include-content # Stores secrets to disk! ### Required .gitignore Entry Add to your .gitignore to prevent accidental commits: # Context verification packets (may contain sensitive data) output/context-packets/ ### Storage and Retention Location: Packets stored in output/context-packets/ (workspace-local) Format: Unencrypted JSON Retention: No automatic deletion; clean up manually Access: Standard filesystem permissions (no additional access controls) For sensitive environments, consider: Restricting output/ directory permissions Using encrypted filesystems Periodic cleanup of old packets ### Provenance This 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. ### Hash Computation Default algorithm: SHA-256 hash(file) = SHA256(file.content) ### Severity Classification Files are auto-classified based on configurable patterns: SeverityDefault PatternsBehavior on Changecritical*.env, *credentials*, *secret*, project configBlock operationimportant*.go, *.ts, *.md (in docs/)Warn userminor*.log, *.tmp, output/*Info only Critical file patterns are configurable via .openclaw/context-verifier.yaml: # .openclaw/context-verifier.yaml critical_patterns: - "*.env" - "*credentials*" - "*secret*" - "CLAUDE.md" # Claude Code projects - "AGENTS.md" # OpenClaw projects - "pyproject.toml" # Python projects - "Cargo.toml" # Rust projects ### Context Packet Structure { "id": "PKT-20260215-001", "created": "2026-02-15T10:30:00Z", "files": [ { "path": "src/main.go", "hash": "abc123...", "severity": "important", "size": 1234, "modified": "2026-02-15T10:00:00Z" } ], "metadata": { "purpose": "pre-refactor snapshot", "creator": "context-verifier" } } ### /cv hash output [HASH] src/main.go Algorithm: SHA-256 Hash: a1b2c3d4e5f6... Size: 1,234 bytes Modified: 2026-02-15 10:00:00 ### /cv verify output (match) [VERIFY] src/main.go Status: ✓ MATCH Expected: a1b2c3d4e5f6... Actual: a1b2c3d4e5f6... ### /cv verify output (mismatch) [VERIFY] src/main.go Status: ✗ MISMATCH Expected: a1b2c3d4e5f6... Actual: x9y8z7w6v5u4... WARNING: File has changed since last read. Action: Re-read file before making changes. ### /cv tag output [TAG] src/main.go Severity: important Reason: Go source file Behavior: Warn on unexpected change ### /cv packet output [PACKET CREATED] ID: PKT-20260215-001 Files: 4 Total size: 10,234 bytes Files included: - src/main.go (important) - a1b2c3... - src/handler.go (important) - d4e5f6... - docs/README.md (important) - j0k1l2... - config/settings.yaml (important) - m3n4o5... Stored: output/context-packets/PKT-20260215-001.json Note: Avoid including sensitive files (.env, credentials) in packets. Use specific globs like src/*.go rather than * to exclude secrets. ### Integration Layer: Foundation (no dependencies) Depends on: None (foundational verification system) Used by: failure-memory (for file change detection), constraint-engine (for pre-action checks) ### Failure Modes 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}" ### Next Steps After invoking this skill: ConditionActionHash mismatchAlert user, suggest re-read of fileCritical file changedBlock operation, require verificationPacket createdStore in output/context-packets/ for audit ### Workspace Files This skill reads/writes: output/ └── context-packets/ └── PKT-YYYYMMDD-XXX.json ### Verify file before editing /cv hash src/main.go # Save hash: a1b2c3d4e5f6... # ... later, before editing ... /cv verify src/main.go a1b2c3d4e5f6 # ✓ MATCH - safe to edit ### Create context packet for refactoring /cv packet src/*.go,internal/**/*.go --name "pre-refactor" # Creates packet with all Go files # ... after refactoring ... # Can compare against packet to see what changed ### Tag sensitive files /cv tag .env # Severity: critical /cv tag src/handler.go # Severity: important ### Verify database migration before deployment /cv packet db/migrations/*.sql --name "pre-deploy-migrations" # Creates packet with all migration files # After staging deployment... /cv verify db/migrations/001_users.sql abc123... # ✓ MATCH - migration file unchanged, safe to deploy to production ### Create API schema verification packet /cv packet api/schemas/*.json,api/openapi.yaml --name "api-schema-v2" # Creates packet with all API schema files for version control ### Acceptance Criteria /cv hash computes SHA-256 hash of file /cv verify compares file hash against expected value /cv verify clearly indicates match/mismatch /cv tag auto-classifies file severity based on patterns /cv tag allows manual severity override /cv packet creates JSON packet with file metadata /cv packet supports glob patterns Critical file changes trigger block behavior Workspace files stored in documented location Consolidated from 3 skills as part of agentic skills consolidation (2026-02-15). ## Trust - Source: tencent - Verification: Indexed source record - Publisher: leegitw - Version: 1.5.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-30T18:48:42.512Z - Expires at: 2026-05-07T18:48:42.512Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/context-verifier) - [Send to Agent page](https://openagent3.xyz/skills/context-verifier/agent) - [JSON manifest](https://openagent3.xyz/skills/context-verifier/agent.json) - [Markdown brief](https://openagent3.xyz/skills/context-verifier/agent.md) - [Download page](https://openagent3.xyz/downloads/context-verifier)