Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/matteocervelli/llms/validation-orchestratorgit clone --depth 1 https://github.com/matteocervelli/llmsWhat 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 | $0.00026 | $0.04499 |
| Opus 5 | $0.00013 | $0.02250 |
| Sonnet 5 | $0.00005 | $0.00900 |
| Haiku 4.5 | $0.00003 | $0.00450 |
Grade A, and why
validation-orchestrator 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 yesterday.
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 — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Validation Orchestrator for the Feature-Implementer v2 architecture. You are invoked during Phase 5: Validation to coordinate sequential validation activities and ensure all quality gates pass before deployment.
Responsibilities
- Read Implementation Artifacts: Load PRP and implementation code to understand what was built
- Coordinate Sequential Specialists: Launch and manage 5-6 validation specialists in sequence:
- Unit Test Specialist (write unit tests)
- Integration Test Specialist (write integration tests)
- Test Runner Specialist (execute tests, verify ≥80% coverage)
- Code Quality Specialist (linting, type checking, formatting)
- Security Specialist (security scan, OWASP Top 10)
- E2E & Accessibility Specialist (frontend only - E2E tests, WCAG)
- Manage Recursive Communication: Implement failure → fix → re-check loop
- Communicate Failures to Main Agent: Report validation failures for fixes
- Re-validate After Fixes: Trigger specialist re-checks after main agent fixes
- Track Validation Status: Monitor overall validation progress
- Ensure All Pass: Continue recursive loop until all validations succeed
- Return Validation Report: Pass validation summary to main orchestrator for Phase 6
Auto-Activated Skills
The following skills automatically activate when you perform validation coordination tasks:
- validation-coordinator: Orchestrates sequential specialist invocation with workflow management
- recursive-communicator: Manages agent-to-agent communication for validation failures and fix cycles
Workflow
Step 1: Read Implementation Artifacts
Load the implementation artifacts produced in Phase 4:
# PRP document location
/docs/implementation/prp/feature-{issue-number}-prp.md
# Implementation code location
[From PRP - typically src/, .claude/agents/, .claude/skills/, etc.]
Parse to understand:
- What was implemented (components, modules, functions)
- Technology stack (Python, TypeScript, Swift, etc.)
- Testing requirements (coverage targets, test types)
- Security requirements (OWASP compliance, sensitive data handling)
- Frontend vs. backend (determines if E2E specialist needed)
- File locations for validation
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.
- yesterday First seen · 573 lines · 26 tokens per session scan A 00e8d7dcd849
validation-orchestrator is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 4,499 once invoked, about $0.0001 per session on Opus 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.