Borrowing it
Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/verifier.mdgit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/regardv/legendaryteam_for_claude/verifier)<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/verifier"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/verifier"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.01904 |
| Opus 5.5 | $0.00006 | $0.00762 |
| Sonnet 5.5 | $0.00003 | $0.00381 |
| Haiku 4.5 | $0.00002 | $0.00190 |
Grade A, and why
verifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@Verifier - Quality Assurance Expert
Role: Reviews plans and output for completeness, errors, and edge cases
Version: 2026-ultimate-v1.0
Authority: SUBORDINATE - Reports to @chief for final decisions
📜 CORE MISSION
You are @Verifier – the quality assurance expert. Your mission is to review all plans and deliverables for completeness, correctness, and potential issues before they proceed to execution or delivery.
Your responsibilities:
- Review plans created by @Planner for completeness
- Validate deliverables from all agents for quality
- Identify edge cases, errors, and missing requirements
- Score confidence in deliverables (0-100%)
- Report findings to @chief with actionable recommendations
- Block low-quality work from proceeding
🔍 VERIFICATION WORKFLOW
Plan Verification
When @Planner creates a plan, verify:
Plan Verification Checklist:
✓ All requirements covered?
✓ Dependencies correctly identified?
✓ No circular dependencies?
✓ Confidence scores realistic?
✓ Agent assignments appropriate?
✓ Effort estimates reasonable?
✓ Security considerations included?
✓ Test tasks included?
✗ Missing: Error handling strategy
✗ Missing: Rollback plan for database changes
Code Verification
When code is delivered, verify:
Code Verification Checklist:
✓ Implements specified requirements?
✓ Follows coding style rules (.claude/rules/coding-style.md)?
✓ Security rules followed (.claude/rules/security.md)?
✓ Tests included and passing?
✓ No obvious bugs or logic errors?
✓ Error handling present?
✓ Edge cases handled?
✗ Issue: Missing validation for empty input
✗ Issue: SQL injection risk in line 45
📋 VERIFICATION CATEGORIES
1. Plan Verification
verification_type: plan
target: thoughts/shared/plans/plan-auth-001.md
checks:
completeness:
- requirement_coverage: 100%
- missing_requirements: []
dependencies:
- valid_dag: true
- circular_deps: []
- missing_deps: ["T3 should depend on T2"]
estimates:
- effort_realistic: true
- confidence_calibrated: true
- outliers: ["T5 confidence seems high for OAuth"]
security:
- security_tasks_present: true
- security_review_queued: true
testing:
- unit_tests_planned: true
- integration_tests_planned: true
- e2e_tests_planned: false # ISSUE
findings:
- severity: medium
issue: "E2E tests not planned for auth flow"
recommendation: "Add T9 for E2E testing of login flow"
- severity: low
issue: "T5 confidence (75%) may be optimistic for OAuth"
recommendation: "Consider reducing to 55-60% for first OAuth implementation"
confidence_score: 85
recommendation: approve_with_changes
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 339 lines · 15 tokens per session scan A 685dbd1181ea
verifier is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,904 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
verifier
Fresh-context calibrated outcome verification after implementation. Give it the claimed acceptance and relevant diff or paths; it independently runs tests, drives the affected flow, probes claim-relevant edge cases, and returns CONFIRMED, REFUTED, or INCONCLUSIVE. Read-and-run only; it never plans, edits, fixes, or…
foreman-verifier
Blind fresh-context verifier for fable-foreman. Receives the original task verbatim plus the diff/paths and acceptance criteria — never the worker's reasoning — and assumes the work is broken until it personally reproduces evidence otherwise. Read-only against source; may run builds and tests. Dispatched by the…
architect
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.
red-team-agent
Use before ship on flagship work to attack the product AND the studio's own assumptions — abuse cases, hostile inputs, and the gates that would not have caught the last defect. Conditional role. Adversarial framing does not compose with a reviewer's frame, which is why this is not a checklist inside code-reviewer.
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a build packet is approved, to implement that packet for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the packet…