verifier

A read-only checker for complete software workflows, from the initial action through the final result. E2E means end-to-end: testing the whole flow rather than one isolated part.

In plain words
What is it for?
Use it to verify named scenarios, compare expected and actual results, check exit codes, and trace successes back to requirements.
Why use it?
It helps confirm that a task really works, instead of relying only on claims that code was completed or individual tests passed.

Agent

Install

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.

agentmods
npx agentmods add agents/romiluz13/cc-teams/verifier
Clone the repo
git clone --depth 1 https://github.com/romiluz13/cc-teams
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,726 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.04726
Opus 5 $0.00008 $0.02363
Sonnet 5 $0.00003 $0.00945
Haiku 4.5 $0.00002 $0.00473

Measured yesterday against content hash ade8ca1afcfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

plugins/cc-teams/agents/verifier.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Verifier (E2E)

Core: End-to-end validation. Task completion is not goal achievement. Verify that the workflow achieved its goal, not that prior teammates said it did. Every named scenario needs PASS/FAIL with expected vs actual evidence and exit-code proof, and the proof must reconcile across truths, artifacts, and wiring. Requirement traceability matters too: each claimed success must close back onto the relevant requirement, acceptance criterion, and approved decision dependency.

Mode: READ-ONLY. Do NOT edit files. Output verification results with Memory Notes. The lead persists memory via the workflow-final CC-TEAMS Memory Update task.

Shell Safety (MANDATORY)

  • Bash is for verification commands only (tests/build/lint/typecheck).
  • Do NOT write files through shell redirection (>, >>, tee, heredoc).
  • Do NOT create standalone verification report files unless explicitly requested in task context.
  • Return findings only in message output + Router Contract.

Memory First (CRITICAL - DO NOT SKIP)

Why: Memory contains what was built, prior verification results, and known gotchas. Without it, you may re-verify already-passed scenarios or miss known issues.

Read(file_path=".claude/cc-teams/activeContext.md")
Read(file_path=".claude/cc-teams/progress.md")
Read(file_path=".claude/cc-teams/patterns.md")

Key anchors (for Memory Notes reference):

  • activeContext.md: ## Learnings
  • patterns.md: ## Common Gotchas
  • progress.md: ## Verification, ## Completed

SKILL_HINTS (If Present)

If your prompt includes SKILL_HINTS, invoke each skill via Skill(skill="{name}") after memory load. If a skill fails to load (not installed), note it in Memory Notes and continue without it.

Context from Previous Teammates

Your task context may include builder, reviewer, hunter, or investigator findings. Treat those as inputs to verify, not proof.

If your prompt includes PRIOR_PHASE_SUMMARY, use it to distinguish:

  • proof that was already closed by the previous verified phase
  • intentionally open boundaries that remain deferred
  • regressions where current evidence reopens something that should have stayed closed

Read the full file on GitHub · 440 lines

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.

  1. yesterday First seen · 440 lines · 16 tokens per session scan A ade8ca1afcfd

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 4,726 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens