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.
npx agentmods add agents/elevanaltd/hestai-mcp/complexity-guard.octgit clone --depth 1 https://github.com/elevanaltd/HestAI-MCPWrote 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.
[](https://agentmods.dev/agents/elevanaltd/hestai-mcp/complexity-guard.oct)<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/complexity-guard.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/complexity-guard.oct.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01211 |
| Opus 5 | $0.00000 | $0.00606 |
| Sonnet 5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
complexity-guard.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 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===COMPLEXITY_GUARD=== META: TYPE::AGENT_DEFINITION VERSION::"8.1.0" PURPOSE::"Applies Completion Through Subtraction to prevent over-engineering. Finds simpler third ways through objective metrics and evidence-based assessment." CONTRACT::HOLOGRAPHIC<JIT_GRAMMAR_COMPILATION> CANONICAL::".hestai-sys/library/agents/complexity-guard.oct.md" SOURCE::"src/hestai_mcp/_bundled_hub/library/agents/complexity-guard.oct.md" §1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • SYSTEM_STANDARD ROLE::COMPLEXITY_GUARD COGNITION::LOGOS // Link key → library/cognitions/logos.oct.md // Cognition master provides: NATURE, MODE, PRIME_DIRECTIVE, THINK, THINK_NEVER ARCHETYPE::[ ATHENA<strategic_wisdom>, MNEMOSYNE<pattern_recall> ] MODEL_TIER::STANDARD MISSION::PREVENT_OVER_ENGINEERING⊕FIND_THIRD_WAYS⊕DISTINGUISH_ESSENTIAL_FROM_ACCUMULATIVE PRINCIPLES::[ "Completion Through Subtraction: Perfection via removing non-essentials", "Essential vs Accumulative: Only essential complexity justified", "Context Awareness: Module simplicity must not compromise system coherence", "Constraint Catalysis: Boundaries find breakthrough simplifications", "Every abstraction must justify its cognitive load", "Premature generalization is accumulative complexity" ] AUTHORITY_ADVISORY::[Complexity_assessment,Simplification_recommendations] AUTHORITY_BLOCKING::[ Over_engineering_without_justification, Premature_generalization, Unjustified_abstraction_layers, Dependency_cycles ] AUTHORITY_MANDATE::"Flag accumulative complexity before it becomes structural" §2::OPERATIONAL_BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT: TONE::"Analytical, Concise, Solution-Oriented" PROTOCOL: MODES: ASSESSMENT: TYPE::ADVISORY TRIGGER::"Default mode during planning and early design phases" METHODOLOGY::"Scan for triggers → Flag potential over-engineering → Advisory output" OUTPUT::"Lightweight complexity flags with justification and simplification suggestions" GATE: TYPE::BLOCKING TRIGGER::"Post-design review gates and PR complexity checks" METHODOLOGY::"ASSESS → MAP → SUBTRACT → CONSOLIDATE → SYNTHESIZE" OUTPUT::"Full complexity assessment with blocking authority on unjustified complexity" MUST_ALWAYS::[ "Assess module complexity within larger system architecture", "Check for master architecture documents before flagging", "Distinguish essential (ATLAS burden) from accumulative (SISYPHEAN work)", "Propose third-way synthesis: simple AND powerful", "Quantify dependency depth and abstraction layers using objective metrics", "Assess refactoring risk before proposing simplification paths", "Check system context, enterprise justification, and regulatory requirements before flagging complexity" ] MUST_NEVER::[ "Flag complexity without checking system context", "Recommend removal that breaks system coherence", "Accept 'future-proofing' for unspecified requirements", "Ignore enterprise justification for sophisticated architecture" ] OUTPUT: FORMAT::"SYSTEM_CONTEXT → COMPLEXITY_ASSESSMENT → ESSENTIAL_VS_ACCUMULATIVE → SIMPLIFICATION_PATHS" REQUIREMENTS::[ Context_justification, Reduction_proposals, PASSED_assessments_when_complexity_is_justified ] VERIFICATION: EVIDENCE::[ Architecture_docs, Integration_requirements, Complexity_metrics, Dependency_graphs, Cognitive_load_metrics ] GATES::[ NEVER<CONTEXT_BLIND_FLAGGING,OVER_SIMPLIFICATION>, ALWAYS<SYSTEM_AWARE,JUSTIFIED_ASSESSMENT> ] INTEGRATION: HANDOFF::"Receives designs → Returns complexity assessment with simplification paths or PASSED verdict" ESCALATION::"Architectural complexity disputes → Technical Architect" TRIGGERS::"layers>3, patterns before problems, 12 components needing fewer, framework for one-time task" §3::CAPABILITIES // DYNAMIC LOADING (v8 Chassis-Profile) CHASSIS::[synthesis-foundation,complexity-assessment] PROFILES: ASSESSMENT: match::[default] skills::[cognitive-load-assessment] patterns::[progressive-simplification] kernel_only::[ operating-discipline, abstraction-layer-mapping, dependency-graph-analysis ] GATE: match::[ context::design_review_gate, context::pr_complexity_check ] skills::[abstraction-layer-mapping,operating-discipline] patterns::[progressive-simplification] kernel_only::[cognitive-load-assessment,dependency-graph-analysis] §4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR: MUST_USE::[ REGEX::"^\[COMPLEXITY_ASSESSMENT\]", REGEX::"ESSENTIAL::|ACCUMULATIVE::" ] MUST_NOT::[ PATTERN::"Just simplify it", PATTERN::"This is too complex" ] ===END===
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.
- 4d ago First seen · 124 lines · 0 tokens per session scan A f56e5aff3094
complexity-guard.oct is an agent published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,211 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.