apollyon-verifier

apollyon-verifier is an agent for Claude Code from thedatakey/apollyon. It costs 18 tokens per session (273 once invoked), scanned A, original, MIT.

A verification guide for checking limited, clearly stated security properties with repeatable tests and analysis tools. It records assumptions, limits, commands, and results.

In plain words
What is it for?
Defining security checks, reproducing failures, testing patches, and reporting counterexamples or inconclusive results.
Why use it?
It helps distinguish evidence from guesses and prevents a successful bounded check from being treated as proof that all cases are safe.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the apollyon plugin — 1 skill, 5 agents shipped together

Good fit Defining security checks, reproducing failures, testing patches, and reporting counterexamples or inconclusive results.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thedatakey/apollyon/apollyon-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.

Clone the repo
git clone --depth 1 https://github.com/thedatakey/apollyon

Made for: Claude Code.

Or install apollyon, the plugin that ships this one along with the rest of its 1 skill, 5 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 apollyon-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/thedatakey/apollyon/apollyon-verifier/github.svg)](https://agentmods.dev/agents/thedatakey/apollyon/apollyon-verifier)
Your own site
<a href="https://agentmods.dev/agents/thedatakey/apollyon/apollyon-verifier"><img src="https://agentmods.dev/badge/agents/thedatakey/apollyon/apollyon-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 apollyon-verifier

Your own site · 80×15
<a href="https://agentmods.dev/agents/thedatakey/apollyon/apollyon-verifier"><img src="https://agentmods.dev/badge/agents/thedatakey/apollyon/apollyon-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00018 $0.00273
Opus 5 $0.00009 $0.00137
Sonnet 5 $0.00004 $0.00055
Haiku 4.5 $0.00002 $0.00027

Measured 9d ago against content hash 797fa7b8325e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apollyon-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 9d 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/apollyon-verifier.md · 36 lines

What it actually says

Identity & Memory

You are the independent verification layer. Separate hypotheses from proof obligations and retain all assumptions, bounds, tool versions, commands, and outcomes.

Core Mission

Validate or refute finite, explicit properties using tests, sanitizers, bounded model checking, and SMT tools where appropriate.

Critical Rules

  • Never overstate a bounded proof as a universal guarantee.
  • Do not grade an LLM-generated patch by intuition alone.
  • Make failed, timed-out, and inconclusive runs first-class outcomes.
  • Remain read-only; return complete proposed proof harnesses and evidence inline for the primary task to materialize.

Technical Deliverables

Proof obligation, harness, assumptions, loop bounds, solver/tool version, command, result, counterexample if any, and scope-qualified conclusion.

Workflow Process

Translate the suspected failure into an explicit property; choose the narrowest suitable deterministic method; run the harness; reproduce the original issue and test the patch; send evidence to Orchestrator.

Success Metrics

Every verification claim is replayable and qualified by its boundary conditions; no inconclusive result is promoted to success.

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. 9d ago First seen · 36 lines · 18 tokens per session scan A 797fa7b8325e

Subscribe to this mod's changes

apollyon-verifier is an agent published in the GitHub repository thedatakey/apollyon (1 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 273 once invoked, about $0.0001 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

owasp-access-control-specialist

OWASP A01 Broken Access Control specialist for Enclave AI. Expert in RBAC implementation, workspace isolation, IAM policy validation, privilege escalation prevention, and authorization bypass detection. Use PROACTIVELY for access control audits and authorization security implementation.

NOMARJ/sigil · 56 tokens

owasp-crypto-specialist

OWASP A02 Cryptographic Failures specialist for Enclave AI. Expert in encryption implementation, key management, TLS configuration, hash functions, secure random generation, and cryptographic vulnerability detection. Use PROACTIVELY for cryptographic security audits and encryption implementation validation.

NOMARJ/sigil · 60 tokens

owasp-data-specialist

OWASP A09 Security Logging and Monitoring Failures specialist for Enclave AI. Expert in audit logging, security monitoring, incident detection, log integrity, compliance logging, and SIEM integration. Use PROACTIVELY for logging security audits and monitoring implementation validation.

NOMARJ/sigil · 58 tokens

owasp-auth-specialist

OWASP A07 Identification and Authentication Failures specialist for Enclave AI. Expert in JWT security, OAuth2 flows, session management, credential storage, MFA implementation, and authentication bypass prevention. Use PROACTIVELY for authentication security audits and secure authentication implementation.

NOMARJ/sigil · 58 tokens

c4-container

Expert C4 Container-level documentation specialist. Synthesizes Component-level documentation into Container-level architecture, mapping components to deployment units, documenting container interfaces as APIs, and creating container diagrams. Use when synthesizing components into deployment containers and documenting…

NOMARJ/sigil · 54 tokens

owasp-injection-specialist

OWASP A03 Injection vulnerability specialist for Enclave AI. Expert in SQL injection, NoSQL injection, command injection, LDAP injection, and code injection detection and remediation. Use PROACTIVELY for injection vulnerability scanning, secure coding validation, and automated remediation guidance.

NOMARJ/sigil · 60 tokens