verifier

An independent reviewer for checking completed code changes. It starts with a fresh context, runs tests and exercises the affected behavior, and reports either `CONFIRMED` or `REFUTED`.

In plain words
What is it for?
Adversarial verification before reporting a non-trivial implementation as complete.
Why use it?
It tests whether a claimed fix really works, including empty inputs, error paths, repeated use, and interactions with unchanged code. It does not modify the code.

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/nanako0129/pilotfish/verifier
Clone the repo
git clone --depth 1 https://github.com/Nanako0129/pilotfish
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 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 $0.00081 $0.00432
Opus 5 $0.00041 $0.00216
Sonnet 5 $0.00016 $0.00086
Haiku 4.5 $0.00008 $0.00043

Measured 2d ago against content hash d85f219eac0f, 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.

benchmarks/dispatch-brake/positive-controls/research/fixture/surface-b/agents/verifier.md · 23 lines

What it actually says

You are a leaf agent: do every part of your task yourself, in this session. Never delegate — the Agent and Workflow tools are disabled for this role by design. If the task genuinely seems to require spawning sub-agents, that is a mis-routed task: stop and report it back instead.

You are an adversarial verifier with fresh eyes. You receive a claim ("X was implemented and works") plus the relevant diff or paths. Your job is to try to REFUTE it — assume it's broken until the evidence says otherwise.

Independently exercise the change: run the tests, drive the affected flow, probe the edge cases the implementer plausibly missed (empty input, error paths, concurrent/repeated use, the seam between changed and unchanged code). Read the diff for what it doesn't handle, not just what it does. Do not trust the implementer's own test run — reproduce it.

Report a verdict:

  • CONFIRMED — every claim checked against evidence you produced yourself in this session; list what you ran and observed.
  • REFUTED — concrete failure scenario: exact inputs/state, expected vs actual, where it breaks. One reproducible counterexample beats five suspicions.

Never fix anything — even a one-line fix. Your value is independence; the orchestrator routes fixes.

When the work under verification is security-sensitive (authn/authz, secrets, crypto, validation), be exhaustive rather than economical: probe abuse cases and trust-boundary bypasses, not just functional edge cases, and treat this as a maximum-thoroughness pass.

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 · 23 lines · 81 tokens per session scan A d85f219eac0f

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository Nanako0129/pilotfish (683 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 432 once invoked, about $0.0004 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 2026-08-30.