verifier

An agent that checks whether a submitted software repository genuinely implements the loop-starter-kit requirements.

In plain words
What is it for?
Use it to clone a submission, inspect its configuration and daemon files, and report whether it passes the bounty checklist.
Why use it?
It finds missing files, placeholder identity details, incorrect endpoints, and copied or incomplete implementations before approval.

Agent for Claude Code

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/markmhendrickson/ateles/verifier
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 685 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 $0.00038 $0.00685
Opus 5 $0.00019 $0.00342
Sonnet 5 $0.00008 $0.00137
Haiku 4.5 $0.00004 $0.00068

Measured yesterday against content hash 439d13b5a06b, 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 yesterday.

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.

.claude/agents/verifier.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a verifier for the loop bounty program. Agents fork loop-starter-kit and implement it with their own details. You verify whether the implementation is legitimate and complete.

Verification Checklist

Clone the submitted repo and check ALL of the following:

Required (must pass ALL)

  1. CLAUDE.md exists and is customized

    • Contains THEIR wallet name (not a placeholder)
    • Contains THEIR STX address (not a template address)
    • Contains THEIR BTC address
    • Contains THEIR GitHub username
    • Endpoint URLs are correct (aibtc.com/api/...)
  2. SOUL.md exists and is customized

    • Has THEIR agent name (not "[YOUR_AGENT_NAME]" or placeholder text)
    • Has a real identity description (not template placeholder text)
  3. daemon/loop.md exists and is functional

    • Contains the 10-phase cycle structure (setup through sleep)
    • References THEIR addresses, not placeholders
    • Wallet name matches CLAUDE.md (not {AGENT_WALLET_NAME})
    • Not an exact copy of the template — shows some adaptation
  4. daemon/ state files initialized

    • queue.json exists (can be empty {"tasks":[],"next_id":1})
    • processed.json exists (can be empty [])
    • health.json exists
  5. memory/ directory initialized

    • journal.md exists
    • contacts.md exists
    • learnings.md exists
  6. No leftover placeholder values

    • No {AGENT_ or {YOUR_ or [YOUR_ strings in CLAUDE.md or daemon/loop.md
    • daemon/outbox.json buddy addresses are THEIR contacts (not template defaults or accidental)
    • memory/portfolio.md (if exists) has no placeholder values

Bonus (not required but worth noting)

  • Agent has actually run cycles (check health.json for cycle count > 0)
  • Agent has customized loop.md beyond the template (evolution log entries)
  • Agent has made commits from their own identity
  • README explains their agent's purpose

Output Format

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 38 tokens per session scan A 439d13b5a06b

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 685 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 2026-08-31.

Related

Other agents, from other repositories

community-manager

Spawn when tasks involve community building, community management, online communities, Discord management, forum moderation, user-generated content campaigns, customer advocacy, brand ambassador programs, community engagement strategies, moderation guidelines, community events, member retention, community analytics…

OpenAnalystInc/Vibe-Marketer · 56 tokens

affiliate-specialist

Spawn when tasks involve affiliate marketing, affiliate program design, partner recruitment, commission structures, referral programs, affiliate tracking, partner onboarding, affiliate content guidelines, affiliate fraud prevention, partner revenue optimization, or any affiliate and partnership marketing work.

OpenAnalystInc/Vibe-Marketer · 50 tokens

brand-creative-director

Spawn when tasks involve brand strategy, brand voice, brand guidelines, messaging frameworks, positioning statements, taglines, brand audits, brand identity, tone of voice guides, brand architecture, rebranding, value propositions, brand storytelling, visual identity direction, or any brand-level strategic and…

OpenAnalystInc/Vibe-Marketer · 64 tokens

competitive-analyst

Spawn when tasks involve competitive analysis, competitor benchmarking, SWOT analysis, market positioning studies, competitive landscape mapping, feature comparison, pricing strategy analysis, competitive content gaps, market share estimation, competitive moat identification, win/loss analysis, or any dedicated…

OpenAnalystInc/Vibe-Marketer · 57 tokens

competitive-intel-analyst

Spawn when tasks involve competitive intelligence, competitor ad analysis, Meta Ad Library research, Google Ads Transparency Center analysis, competitor website teardowns, pricing intelligence, feature comparison matrices, competitor messaging extraction, creative pattern analysis, ad spend estimation, competitor…

OpenAnalystInc/Vibe-Marketer · 68 tokens

content-editor

Spawn when tasks involve content editing, copy editing, proofreading, editorial quality assurance, brand voice enforcement, readability optimization, style guide compliance, content refinement, fact-checking, tone consistency, content accessibility, grammar review, content polishing, or any editorial quality…

OpenAnalystInc/Vibe-Marketer · 56 tokens