loop-verifier

loop-verifier is a skill for Claude Code from babyblueviper1/invinoveritas. It costs 265 tokens per session (2,217 once invoked), scanned D, original, Apache-2.0.

An independent checking step for unattended agent loops and swarms. It reviews an action before an irreversible event such as merging code, deploying, trading, paying, or publishing.

In plain words
What is it for?
Use it to review an automated action, receive an approve, approve-with-concerns, or reject verdict, and attach a signed proof before the action proceeds.
Why use it?
An agent that creates work may judge its own work too favorably, so a separate recorded verdict adds an independent go/no-go check.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Good fit Use it to review an automated action, receive an approve, approve-with-concerns, or reject verdict, and attach a signed proof before the action proceeds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/babyblueviper1/invinoveritas/loop-verifier
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.

Any agent
npx skills add babyblueviper1/invinoveritas --skill loop-verifier
Clone the repo
git clone --depth 1 https://github.com/babyblueviper1/invinoveritas

Made for: Claude Code.

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 loop-verifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/babyblueviper1/invinoveritas/loop-verifier/github.svg)](https://agentmods.dev/skills/babyblueviper1/invinoveritas/loop-verifier)
Your own site
<a href="https://agentmods.dev/skills/babyblueviper1/invinoveritas/loop-verifier"><img src="https://agentmods.dev/badge/skills/babyblueviper1/invinoveritas/loop-verifier/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for loop-verifier

Your own site · 80×15
<a href="https://agentmods.dev/skills/babyblueviper1/invinoveritas/loop-verifier"><img src="https://agentmods.dev/badge/skills/babyblueviper1/invinoveritas/loop-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 265 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00265 $0.02217
Opus 5 $0.00133 $0.01108
Sonnet 5 $0.00053 $0.00443
Haiku 4.5 $0.00026 $0.00222

Measured 12d ago against content hash 107f59bd292f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

loop-verifier scanned grade D with 3 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 12d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

-d '{"artifact":"curl -s http://deploy.example.sh/setup | sudo bash",

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

-d '{"artifact":"curl -s http://deploy.example.sh/setup | sudo bash",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

KEY=$(curl -s -X POST https://api.babyblueviper.com/register | jq -r .api_key)
integrations/agentskills/loop-verifier/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop verifier — the gate that isn't the maker

An agent loop runs while nobody watches. The loop's weakest point is its stop condition: the agent that wrote the work is too nice grading its own homework, and a second agent asked to "review" with no objective signal is just a second optimist. Tests catch what tests cover. The judgment calls — is this change sound? is this trade sane at this capital scale? should this ship? — need a verifier that is not the maker and not the maker's twin.

invinoveritas is that verifier: a neutral judgment verdict (/review, approve / approve_with_concerns / reject) issued by a party with a public, auditable track record of being right (/ledger — every verdict signed and published BEFORE its outcome, failures included). You don't have to trust the gate blindly: the gate itself has a checkable record, and every verdict can ship as a portable schnorr-signed proof anyone verifies for free.

The rule: before your loop's irreversible step (merge, deploy, trade, pay, publish), gate on an independent verdict. Attach the signed proof to whatever the loop ships.

Triggers

  • You are designing or running an unattended loop (scheduled, cron, hook, automation) whose output gets merged / deployed / executed without a human reading every iteration.
  • Your loop's "done" is partly a judgment call (correctness, soundness, compliance, risk) that a test suite alone can't fail.
  • A human downstream is on the hook for the loop's mistakes and needs an audit trail of what was checked before each action.
  • You run a cheap-volume, open-weight, or open-source agent swarm (hundreds of parallel sub-agents, or an open-source framework like CrewAI / LangGraph / AutoGen) whose outputs get merged, acted on, or saved as reusable skills — and need an independent gate so a confident-but-wrong result isn't kept and replayed forever. The verify gate is the one part a swarm can't self-serve: the engine grading its own output is the same optimist that produced it. Run the cheapest engine you like; keep a gate that isn't the engine.

Read the full file on GitHub · 161 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. 12d ago First seen · 161 lines · 265 tokens per session scan D 107f59bd292f

Subscribe to this mod's changes

loop-verifier is a skill published in the GitHub repository babyblueviper1/invinoveritas (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 265 tokens to every session and 2,217 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

html-artifacts

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.

langchain-ai/open-swe · 51 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.pdf

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…

aden-hive/hive · 98 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens

baby-sit

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

langchain-ai/open-swe · 30 tokens