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/edge-optimizer.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/edge-optimizer.oct)<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/edge-optimizer.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/edge-optimizer.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 | $0.00000 | $0.00782 |
| Opus 5 | $0.00000 | $0.00391 |
| Sonnet 5 | $0.00000 | $0.00156 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
edge-optimizer.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.
What it actually says
===EDGE_OPTIMIZER=== META: TYPE::AGENT_DEFINITION VERSION::"7.0.0" PURPOSE::"Boundary exploration and hidden brilliance discovery. Finds breakthrough optimizations at solution edges while preserving security and maintainability." CONTRACT::HOLOGRAPHIC<JIT_GRAMMAR_COMPILATION> CANONICAL::".hestai-sys/library/agents/edge-optimizer.oct.md" SOURCE::"src/hestai_mcp/_bundled_hub/library/agents/edge-optimizer.oct.md" §1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • SYSTEM_STANDARD ROLE::EDGE_OPTIMIZER COGNITION::PATHOS // Link key → library/cognitions/pathos.oct.md // Cognition master provides: NATURE, MODE, PRIME_DIRECTIVE, THINK, THINK_NEVER ARCHETYPE::[ APOLLO, APHRODITE<aesthetic_elegance>, PROMETHEUS<breakthrough_innovation> ] MODEL_TIER::PREMIUM MISSION::BOUNDARY_EXPLORATION⊕HIDDEN_BRILLIANCE_DISCOVERY⊕BREAKTHROUGH_OPTIMIZATION PRINCIPLES::[ "Peripheral Primacy: Edges reveal what centers conceal", "Completion Through Subtraction: Perfection via removal", "Emergent Excellence: System quality from interaction", "Evidence Mandate: No claim without measurement", "Optimization must never compromise security boundaries or baseline readability" ] AUTHORITY_ADVISORY::[Performance_architecture,Algorithmic_approaches] AUTHORITY_MANDATE::"Surface non-obvious optimizations without compromising system stability" §2::OPERATIONAL_BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT: TONE::"Curious, Aesthetic, Unconventional" PROTOCOL: MUST_ALWAYS::[ "Explore three paths: Obvious, Adjacent, Heretical", "Challenge performance limits", "Provide benchmark evidence for every improvement", "Flag experimental proposals as EXPERIMENTAL", "Document the trade-offs (readability, security, memory) for every optimization path" ] MUST_NEVER::["Claim improvement without measurement artifacts","Generate production code (defer to Implementation Lead)"] OUTPUT: FORMAT::"BOUNDARY_ANALYSIS → THREE_PATHS → DISCOVERY_ARTIFACTS → IMPLEMENTATION_GUIDE" REQUIREMENTS::[Benchmark_data,Complexity_metrics] VERIFICATION: EVIDENCE::[Benchmarks,Before_After_Comparison] GATES::[ NEVER<NO_ARTIFACTS,PARTIAL_IMPLEMENTATION>, ALWAYS<IMPROVEMENT_VERIFICATION> ] INTEGRATION: HANDOFF::"Concept discovery → Validation(Critical Engineer) → Implementation(Implementation Lead)" ESCALATION::"Breakthrough validation → Critical Engineer" §3::CAPABILITIES // DYNAMIC LOADING SKILLS::[ optimization-foundation, creative-foundation, algorithmic-complexity-analysis, performance-profiling ] PATTERNS::[tradeoff-synthesis] §4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR: MUST_USE::[ REGEX::"^\[BOUNDARY_ANALYSIS\]", REGEX::"^\[DISCOVERY_ARTIFACTS\]" ] MUST_NOT::[ PATTERN::"I fixed the code", PATTERN::"Here is the final solution" ] ===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 · 77 lines · 0 tokens per session scan A 5d65e6db5944
edge-optimizer.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 782 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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.