/verify

name: verify
license: MIT
compatibility: "Claude Code 2.1.277+. Requires memory MCP server."
description: "Grades work for merge: runs unit, integration and E2E suites plus security and type checks, scores 0-10 with a VERIFIED vs CLAIMED manifest. Use when deciding if work can ship. Not for adding missing tests (use cover)."
argument-hint: "[feature-or-scope]"
user-invocable: true
allowed-tools: "SendMessage AskUserQuestion Bash Read Write Edit Grep Glob Agent Workflow TaskCreate TaskUpdate TaskList TaskStop mcp__memory__search_nodes ToolSearch CronCreate CronDelete Monitor PushNotification"
skills: [code-review-playbook, testing-unit, testing-e2e, testing-llm, testing-integration, testing-perf, memory, quality-gates, chain-patterns, browser-tools]
effort: high
model: sonnet
hooks:
  PreToolUse:
    - matcher: "Bash"
      hooks:
        - type: command
          command: "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.mjs skill/test-framework-detector"
          once: true
    - matcher: "Agent"
      hooks:
        - type: command
          command: "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.mjs skill/verify-scoring-rubric-loader"
          once: true
metadata:
  category: workflow-automation
  mcp-server: memory
  version: "4.7.0"
  author: "OrchestKit"
  complexity: "high"
  tags: "verification, testing, quality, validation, parallel-agents, grading"
triggers:
  keywords: [verify, verifiy, validate, verification, "ready for merge", "check everything", "security scan", "give me a score", "full verification", "grade my", "verified vs claimed", "what did you actually verify", "prove it"]
  examples:
    - "verify the authentication implementation"
    - "is this feature ready for merge? check everything"
    - "run tests, security scan, and give me a score"
  anti-triggers: [implement, build, fix, cover, "generate tests", commit]

Verify Feature

Host-neutral workflow. Invoke by skill name (`verify`). Claude Code slash routing, YAML hook loaders, and `.claude/chain` live in `references/claude-code.md`.

Comprehensive verification using parallel specialized agents with nuanced grading (0-10 scale) and improvement suggestions.

Quick Start

verify authentication flow
verify --model=opus user profile feature
verify --scope=backend database migrations

Argument Resolution

A pronoun target (`this`, `them`, `the above`) is read back from the conversation, announced in one line, and used: `Read("../../shared/rules/target-resolution.md")`, inline half.

SCOPE = "$ARGUMENTS"       # Full argument string, e.g., "authentication flow"
SCOPE_TOKEN = "$ARGUMENTS[0]"  # First token for flag detection (e.g., "--scope=backend")
# $ARGUMENTS[0], $ARGUMENTS[1] etc. for indexed access (CC 2.1.59)

# Model override detection (CC 2.1.72)
MODEL_OVERRIDE = None
for token in "$ARGUMENTS".split():
    if token.startswith("--model="):
        MODEL_OVERRIDE = token.split("=", 1)[1]  # "opus", "sonnet", "haiku", "fable"
        SCOPE = SCOPE.replace(token, "").strip()

# Streak gate detection (#2540) — consecutive-pass mode
STREAK_TARGET = None
for token in "$ARGUMENTS".split():
    if token.startswith("--streak="):
        STREAK_TARGET = int(token.split("=", 1)[1])  # N consecutive READY verdicts required (N >= 2)
        SCOPE = SCOPE.replace(token, "").strip()
# When set, apply the Streak Gate (see below). Full protocol: references/streak-gate.md

Pass `MODEL_OVERRIDE` to all Agent() calls via `model=MODEL_OVERRIDE` when set. Accepts symbolic names (`opus`, `sonnet`, `haiku`, `fable` on harnesses whose Agent tool lists it; note fable is premium API spend after 2026-07-12) or full IDs (`claude-opus-5-5`) per CC 2.1.74.

> **Opus 5.5**: Agents use native adaptive thinking (no MCP sequential-thinking needed). Opus 5.5's own effort default is `medium`, one level below Opus 5's `high`, and CC 2.1.280+ starts a newly released model at its default, so pass `high` or `xhigh` for verification. Extended 128K output supports comprehensive verification reports.

---

STEP 0: Effort-Aware Verification Scaling

Scale verification depth based on `/effort` level:

| Effort Level | Phases Run | Agents | Output | |-------------|------------|--------|--------| | **low** | Run tests only → pass/fail | 0 agents | Quick check | | **medium** | Tests + code quality + security + API compliance | 4 agents | Score + top issues | | **high** (default) | All 8 phases + 2.5 visual capture | 6 agents | Full report + grades | | **xhigh** | All 8 phases + 2.5 visual capture + cross-file pattern sweep + self-verification pass | 6 agents | Full report with uncertainty annotations |

> **Override:** Explicit user selection (e.g., "Full verification") overrides `/effort` downscaling.

STEP 0a: Verify User Intent with AskUserQuestion

**BEFORE creating tasks**, clarify verification scope:

AskUserQuestion(
  questions=[{
    "question": "What scope for this verification?",
    "header": "Scope",
    "options": [
      # multiSelect questions do not render previews (single-select only) — kept text-only
      {"label": "Full verification (Recommended)", "description": "All tests + security + code quality + visual + grades"},
      {"label": "Tests only", "description": "Run unit + integration + e2e tests"},
      {"label": "Security & code quality", "description": "Security audit (OWASP/CVE/secrets) + lint/types/complexity"},
      {"label": "Quick check", "description": "Just run tests, skip detailed analysis"}
    ],
    "multiSelect": true
  }]
)

**Based on answer, adjust workflow:**

• **Full verification**: All 8 phases plus 2.5 (visual capture), 6 parallel Phase 2 agents
• **Tests only**: Skip Phase 2 (agent dispatch) and 2.5 (visual capture)
• **Security & code quality**: Run security-auditor + code-quality-reviewer agents
• **Quick check**: Run tests only, skip grading and suggestions (skips Phase 2, outside the Fan-out rule)

---

STEP 0b: Select Orchestration Mode

Load details: `Re