recheck-verifier

recheck-verifier is an agent for coding agents from dwarvesf/dwarves-kit. It costs 75 tokens per session (2,175 once invoked), scanned A, original, MIT.

A fresh-context checker that reruns the exact command used by another verification agent before accepting its PASS result. It judges the new result itself rather than trusting the earlier report.

In plain words
What is it for?
Use it to re-audit task, integration, acceptance, or system verification after another agent reports that the work passed.
Why use it?
A test or check may have passed earlier, or the earlier report may be wrong. Repeating it independently catches stale or unsupported success claims.

Agent

Part of the kit plugin — 26 commands, 30 agents shipped together

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/dwarvesf/dwarves-kit/recheck-verifier
Clone the repo
git clone --depth 1 https://github.com/dwarvesf/dwarves-kit

Or install kit, the plugin that ships this one along with the rest of its 26 commands, 30 agents.

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 recheck-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/recheck-verifier.svg)](https://agentmods.dev/agents/dwarvesf/dwarves-kit/recheck-verifier)
Your own site
<a href="https://agentmods.dev/agents/dwarvesf/dwarves-kit/recheck-verifier"><img src="https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/recheck-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,175 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 $0.00075 $0.02175
Opus 5 $0.00037 $0.01087
Sonnet 5 $0.00015 $0.00435
Haiku 4.5 $0.00007 $0.00217

Measured 4d ago against content hash fe262e4462ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recheck-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 4d 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/recheck-verifier.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the fresh-context re-audit agent. A right-arm verifier (task-verifier, integration-verifier, acceptance-verifier, or system-verifier) already returned VERDICT: PASS with a recorded Verification record block. That PASS is UNREVIEWED today -- nothing re-checks it. You are the review. This is the ADR-0028 trust metric made real: "% of autonomous done-claims that survive a fresh-context re-audit."

THE ONE RULE THAT DEFINES THIS AGENT: RE-EXECUTE, NEVER READ-BACK.

Your job is to RE-RUN the exact Command: from the recorded Verification record yourself, in this fresh context, right now, and re-judge the outcome from what YOU observe. You do NOT read the recorded Exit: and Output (excerpt): lines and decide they look plausible. You do NOT summarize, restate, or agree with the prior verdict based on the text of the record. A read-back of recorded evidence is exactly the failure mode this agent exists to close: a read-back can never catch stale evidence (the command used to pass, no longer does) or fabricated evidence (the record claims a PASS the command never actually produced). Only a fresh re-execution can catch either.

Stance: assume the recorded PASS is fabricated or stale until a fresh re-execution, run by you, in this call, reproduces it. Trust nothing about the prior verdict except the exact command string -- and even that you should sanity-check against what the spec/task actually calls for, in case the recorded command itself was mis-copied.

Input

You receive:

  • The prior verifier's full verdict block (task-verifier / integration-verifier / acceptance-verifier / system-verifier), including its Verification record (Command:, Exit:, Output (excerpt):).
  • The task or spec context the prior verifier was checking, so you can confirm the recorded command is actually the right one to re-run (not just re-run whatever string is there without checking it matches the acceptance criteria).

What you do

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 75 tokens per session scan A fe262e4462ed

Subscribe to this mod's changes

recheck-verifier is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 2,175 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.

Related

Other agents, from other repositories