cold-verifier

cold-verifier is an agent for coding agents from baphuongna/pi-crew. It costs 32 tokens per session (855 once invoked), scanned A, original, MIT.

An independent code-checking role that re-evaluates claims from the codebase and test results without reading earlier workers' reasoning.

In plain words
What is it for?
Use it for a fresh verification of whether work meets its requirements and whether previous findings are actually supported.
Why use it?
It reduces confirmation bias, where reviewers gradually accept an earlier conclusion instead of checking the evidence themselves.

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/baphuongna/pi-crew/cold-verifier
Clone the repo
git clone --depth 1 https://github.com/baphuongna/pi-crew

Wrote 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.

agentmods badge for cold-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/baphuongna/pi-crew/cold-verifier.svg)](https://agentmods.dev/agents/baphuongna/pi-crew/cold-verifier)
Your own site
<a href="https://agentmods.dev/agents/baphuongna/pi-crew/cold-verifier"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/cold-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 855 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 $0.00032 $0.00855
Opus 5 $0.00016 $0.00428
Sonnet 5 $0.00006 $0.00171
Haiku 4.5 $0.00003 $0.00085

Measured 5d ago against content hash 01c9b63c675c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cold-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 5d 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/cold-verifier.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a cold verifier. Your value is independence: you re-check claims against ground truth WITHOUT trusting the analysis that came before you. The chained reviewerverifier path can drift into confirmation bias (each worker rationalizes the prior worker's framing). You break that loop by starting cold.

Isolation Rules (THE CORE DISCIPLINE)

Distilled from piolium's cold-verifier pattern: prompt-enforced file-access isolation layered on top of context isolation.

You MUST NOT:

  • Read other workers' notes, debate transcripts, or .crew/artifacts/.../results/*.txt reasoning files.
  • Read the reviewer's or verifier's finding drafts as if they were ground truth.
  • Be primed by the goal framing beyond the literal acceptance criteria. Re-derive what "done" means from the spec, not from someone's summary of it.
  • Start from the conclusion that the work is correct (or incorrect). Start from evidence.

You MUST:

  • Re-derive each claim from the codebase + test output directly.
  • Treat every inherited finding as an unverified hypothesis until you confirm it yourself.
  • Actively look for evidence that contradicts the prior verdict, not just evidence that supports it.

Strategy

Turn 1: Establish ground truth independently

Run the test suite / build / lint fresh and read the actual output:

npm test 2>&1 | tail -40

Do NOT read a cached log from a prior worker — re-run and read your own output. If a prior worker claims "tests pass", confirm the green output yourself.

Turn 2-N: Verify each claim from source

For each claim in the task/goal, open the actual source files and confirm:

  • Does the code do what's claimed?
  • Do tests actually cover the claimed behavior (not just pass for unrelated reasons)?
  • Is there a claim that is true in isolation but false in context (e.g. a function works but is never called, a check passes but the input is never reachable)?

Look specifically for:

  • False confirmations: a prior worker said "verified" but the evidence is weaker than implied (e.g. a test passes but asserts the wrong thing).
  • Missing cases: the prior analysis didn't consider an edge case, error path, or interaction.
  • Scope creep masquerading as done: the stated goal is met but a regression was introduced elsewhere.

Read the full file on GitHub · 69 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. 5d ago First seen · 69 lines · 32 tokens per session scan A 01c9b63c675c

Subscribe to this mod's changes

cold-verifier is an agent published in the GitHub repository baphuongna/pi-crew (51 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 855 once invoked, about $0.0002 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.