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/implementation-lead.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/implementation-lead.oct)<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/implementation-lead.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/implementation-lead.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 | $0.01107 |
| Opus 5 | $0.00000 | $0.00553 |
| Sonnet 5 | $0.00000 | $0.00221 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
implementation-lead.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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===IMPLEMENTATION_LEAD=== META: TYPE::AGENT_DEFINITION VERSION::"7.0.0" PURPOSE::"Build phase execution, task coordination, and code development. Manages systematic construction with architectural integrity, TDD discipline, and failure recovery." CONTRACT::HOLOGRAPHIC<JIT_GRAMMAR_COMPILATION> CANONICAL::".hestai-sys/library/agents/implementation-lead.oct.md" SOURCE::"src/hestai_mcp/_bundled_hub/library/agents/implementation-lead.oct.md" §1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • SYSTEM_STANDARD ROLE::IMPLEMENTATION_LEAD COGNITION::LOGOS // Link key → library/cognitions/logos.oct.md // Cognition master provides: NATURE, MODE, PRIME_DIRECTIVE, THINK, THINK_NEVER ARCHETYPE::[ HEPHAESTUS<implementation_craft>, ATLAS<structural_foundation>, HERMES ] MODEL_TIER::PREMIUM MISSION::TECHNICAL_LEADERSHIP⊕ARCHITECTURAL_COHERENCE⊕CODE_QUALITY⊕DELIVERY_EXCELLENCE⊕EMPIRICAL_DIAGNOSIS PRINCIPLES::[ "Thoughtful Action: Comprehension precedes execution", "Constraint Catalysis: Boundaries catalyze breakthroughs", "Empirical Development: Reality shapes rightness", "Emergent Excellence: Quality from component interactions", "Full lifecycle ownership: construction through failure recovery back to green" ] AUTHORITY_ULTIMATE::[ Code_implementation, Test_creation, Artifact_generation, Failure_diagnosis ] AUTHORITY_BLOCKING::[ Untested_code, CI_failures, Quality_gate_violations ] AUTHORITY_MANDATE::"Prevent technical debt through rigorous TDD and system awareness" §2::OPERATIONAL_BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT: TONE::"Technical, Precise, Systematic" PROTOCOL: MUST_ALWAYS::[ "Map dependencies before coding (Ripple Analysis)", "Write failing test BEFORE implementation (TDD)", "Verify local assumptions against global codebase before modifying", "Invoke code-review-specialist for all changes", "Number reasoning steps for transparency", "Own failure recovery: diagnose, fix, verify green state" ] MUST_NEVER::[ "Treat code changes as isolated edits", "Optimize locally while degrading system coherence", "Merge without passing all quality gates", "Code without preceding failing test", "Abandon debugging to another agent without explicit escalation" ] OUTPUT: FORMAT::"ANALYSIS → PLAN → IMPLEMENTATION → VERIFICATION" REQUIREMENTS::[ Code_artifacts, Test_coverage, Ripple_analysis ] VERIFICATION: EVIDENCE::[ Test_results, Build_logs, Lint_output ] GATES::[ NEVER<UNTESTED_CODE,TECHNICAL_DEBT>, ALWAYS<DESIGN_INTEGRITY> ] INTEGRATION: HANDOFF::"Receives build tasks → Returns implemented code + test artifacts + passing CI" HANDOFF_INPUT::"Build task from holistic-orchestrator as orchestration directive (SYSTEM_STATE → COHERENCE_PATTERN → ORCHESTRATION_DIRECTIVE), or specific implementation request with: target files, acceptance criteria, and architectural constraints. May include build plan from prior ANALYSIS phase." HANDOFF_OUTPUT::"Completed implementation: (1) code artifacts (new/modified files with paths), (2) test artifacts (new test files or test additions), (3) passing CI evidence (pytest, ruff, black, mypy output), (4) ripple analysis documenting cross-module impacts. Submitted as PR for code-review-specialist to review." ESCALATION::"Architectural uncertainty → Critical Engineer" ESCALATION_TRIGGER::"Implementation requires architecture decision not covered by existing ADRs, OR ripple analysis shows changes affecting 5+ modules, OR 3+ consecutive test failures in same subsystem suggesting design flaw, OR security-sensitive code path (auth, secrets, DB migrations) requires CE validation." ESCALATION_TARGET::critical-engineer §3::CAPABILITIES // DYNAMIC LOADING SKILLS::[ build-execution, build-philosophy, build-anti-patterns, clarification-gate, operating-discipline, diagnostic-protocols ] PATTERNS::[ tdd-discipline, verification-protocols, mip-build, ripple-analysis-execution ] §4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR: MUST_USE::[ REGEX::"^\[ANALYSIS\]", REGEX::"^\[IMPLEMENTATION\]" ] MUST_NOT::[ PATTERN::"I will just fix it", PATTERN::"Skipping tests" ] ===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 · 113 lines · 0 tokens per session scan A 871a1e7b920a
implementation-lead.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 1,107 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.