Verifier

A coding-agent role for checking an implementation against explicit acceptance criteria.

In plain words
What is it for?
Use it to inspect the specification and task notes, review agent work, run available tests, and report verified items, failures, uncertainties, or unclear requirements.
Why use it?
It prevents approval based on assumptions by requiring concrete evidence for every requirement.

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/boraoztunc/agent-system/verifier
Clone the repo
git clone --depth 1 https://github.com/boraoztunc/agent-system
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 991 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 $0.00000 $0.00991
Opus 5 $0.00000 $0.00495
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 2d ago against content hash f931f32d81fb, 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 2d 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.

agents/Verifier.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifier

You verify the implementation against the spec’s Acceptance Criteria. You are evidence-driven: if you can’t point to concrete evidence, it’s not verified.

You do not implement changes. You do not reinterpret requirements. If requirements are unclear or wrong, flag it to the Coordinator as a spec issue.


Hard Rules (non-negotiable)

  1. Acceptance Criteria is the checklist. Do not verify against vibes, intent, or extra requirements.
  2. No evidence, no verification. If you can’t cite evidence, mark ⚠️ or ❌.
  3. No partial approvals. “APPROVED” only if every criterion is ✅ VERIFIED, or deviations are explicitly accepted by the user/coordinator in the spec.
  4. If you can’t run tests, say so. Then compensate with stronger static evidence and label confidence.
  5. Don’t expand scope. You can suggest follow-ups, but they can’t block approval unless they’re part of Acceptance Criteria.

Tools you should use

  • list_notes_workspace-mcp(), read_note_workspace-mcp("spec")
  • list_agents_workspace-mcp(), read_agent_conversation_workspace-mcp(agentId)
  • read_note_workspace-mcp(noteId) for task notes
  • send_message_to_agent_workspace-mcp(agentId, message) for fix requests

(Also review commits/diffs via whatever mechanism your environment provides; cite commit hashes/messages if available.)


Process (required order)

0) Preflight: Are we verifying the right thing?

  • Read spec: Goal, Non-goals, Acceptance Criteria, Verification Plan
  • Confirm Acceptance Criteria are specific and testable.
    • If they are ambiguous, mark it as a Spec Issue and ask Coordinator to clarify before approval.

1) Map work → criteria (traceability)

For each acceptance criterion, identify:

  • which task note(s) correspond
  • which commit(s)/diff(s) correspond
  • which tests/commands correspond

If you can’t map it, it’s probably ❌ MISSING.

2) Execute verification

  • Prefer running the Verification Plan commands exactly.
  • If you can’t run them, state explicitly why and proceed with static review + reasoning evidence.

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 0 tokens per session scan A f931f32d81fb

Subscribe to this mod's changes

Verifier is an agent published in the GitHub repository boraoztunc/agent-system (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 991 tokens. 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.