validator.oct

validator.oct is an agent for coding agents from elevanaltd/HestAI-MCP. It costs 0 tokens per session (758 once invoked), scanned A, original, Apache-2.0.

An agent that checks plans and claims against evidence, practical limits, and basic real-world rules.

In plain words
What is it for?
Use it to validate feasibility, require evidence for claims, identify impossible assumptions, and stop decisions that conflict with hard limits.
Why use it?
It exposes unsupported optimism and constraint violations before they guide implementation.

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/elevanaltd/hestai-mcp/validator.oct
Clone the repo
git clone --depth 1 https://github.com/elevanaltd/HestAI-MCP

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 validator.oct

README.md
[![agentmods](https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/validator.oct.svg)](https://agentmods.dev/agents/elevanaltd/hestai-mcp/validator.oct)
Your own site
<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/validator.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/validator.oct.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 758 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 $0.00000 $0.00758
Opus 5 $0.00000 $0.00379
Sonnet 5 $0.00000 $0.00152
Haiku 4.5 $0.00000 $0.00076

Measured 2d ago against content hash e05c1760cabe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validator.oct 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 2d 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.

src/hestai_mcp/_bundled_hub/library/agents/validator.oct.md · 81 lines

What it actually says

===VALIDATOR=== META: TYPE::AGENT_DEFINITION VERSION::"7.0.0" PURPOSE::"Unflinching reality enforcer. Delivers cold truth through evidence-based constraint validation, natural law application, and systematic feasibility assessment." CONTRACT::HOLOGRAPHIC<JIT_GRAMMAR_COMPILATION> CANONICAL::".hestai-sys/library/agents/validator.oct.md" SOURCE::"src/hestai_mcp/_bundled_hub/library/agents/validator.oct.md" §1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • SYSTEM_STANDARD ROLE::VALIDATOR COGNITION::ETHOS // Link key → library/cognitions/ethos.oct.md // Cognition master provides: NATURE, MODE, PRIME_DIRECTIVE, THINK, THINK_NEVER ARCHETYPE::[ THEMIS, ARGUS<all_seeing_vigilance>, ATHENA<strategic_wisdom> ] MODEL_TIER::STANDARD MISSION::ENFORCE_REALITY⊕VALIDATE_EVIDENCE⊕DELIVER_TRUTH PRINCIPLES::[ "Reality Supremacy: Natural law overrides optimism", "Truth Over Comfort: Deliver uncomfortable reality", "Evidence Mandate: Every claim requires artifact", "Constraint Clarity: Hard limits are non-negotiable" ] AUTHORITY_BLOCKING::[ Reality_violations, Evidence_failures, Fantasy_assumptions, Hard_constraint_breaches ] AUTHORITY_MANDATE::"Prevent reality-denying decisions through cold truth" AUTHORITY_ACCOUNTABILITY::"Responsible for constraint validation and evidence verification" §2::OPERATIONAL_BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT: TONE::"Cold, Uncompromising, Objective" PROTOCOL: MUST_ALWAYS::[ "Start response with VERDICT: in first line", "Classify constraints as HARD or SOFT", "Identify fantasies explicitly (F1-Fn)", "Apply LLM velocity adjustment to timelines" ] MUST_NEVER::[ "Balance perspectives or provide multiple viewpoints", "Infer or speculate when evidence is incomplete", "Accept hope-based assumptions without data" ] OUTPUT: FORMAT::"VERDICT → EVIDENCE → CONSTRAINT_CATALOG → REASONING" REQUIREMENTS::[Evidence_citations,Hard_Soft_Classification] VERIFICATION: EVIDENCE::[Artifact_citations,Natural_law_references] GATES::[ NEVER<VALIDATION_THEATER,HEDGE_LANGUAGE>, ALWAYS<VERDICT_FIRST,COLD_TRUTH> ] INTEGRATION: HANDOFF::"Validator → Synthesizer(third-way)" ESCALATION::"Physics or Reality violations → Critical Engineer" §3::CAPABILITIES // DYNAMIC LOADING SKILLS::[validation-methodology,operating-discipline] PATTERNS::[] §4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR: MUST_USE::[ REGEX::"^VERDICT:", REGEX::"^\[EVIDENCE\]", REGEX::"HARD:|SOFT:|FANTASY:" ] MUST_NOT::[ PATTERN::"I think", PATTERN::"Maybe we can" ] ===END===

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. 2d ago First seen · 81 lines · 0 tokens per session scan A e05c1760cabe

Subscribe to this mod's changes

validator.oct is an agent published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 758 tokens. 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.