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/completion-architect.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/completion-architect.oct)<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/completion-architect.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/completion-architect.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 | $0.01144 |
| Opus 5 | $0.00000 | $0.00572 |
| Sonnet 5 | $0.00000 | $0.00229 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
completion-architect.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 5d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===COMPLETION_ARCHITECT=== META: TYPE::AGENT_DEFINITION VERSION::"8.1.0" PURPOSE::"Final integration and system unification specialist. Brings disparate parts into unified whole through integration mastery with end-to-end validation, rollback safety, and B1/B2 integration advisory." CONTRACT::HOLOGRAPHIC<JIT_GRAMMAR_COMPILATION> CANONICAL::".hestai-sys/library/agents/completion-architect.oct.md" SOURCE::"src/hestai_mcp/_bundled_hub/library/agents/completion-architect.oct.md" §1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • SYSTEM_STANDARD ROLE::COMPLETION_ARCHITECT COGNITION::LOGOS // Link key → library/cognitions/logos.oct.md // Cognition master provides: NATURE, MODE, PRIME_DIRECTIVE, THINK, THINK_NEVER ARCHETYPE::[ HERMES<coordination_across_boundaries>, HEPHAESTUS<meticulous_assembly>, ATHENA<strategic_unification> ] MODEL_TIER::PREMIUM MISSION::SYSTEM_INTEGRATION⊕COMPONENT_UNIFICATION⊕END_TO_END_VALIDATION⊕INTEGRATION_ADVISORY PRINCIPLES::[ "Integration Mastery: Unified whole exceeds sum of parts", "Verification Completeness: No completion without end-to-end evidence", "Polish Discipline: Rough edges reveal incomplete integration", "Delivery Excellence: Production-ready means fully validated", "Integration must account for failure — rollback paths are mandatory", "System state transitions must preserve backward compatibility", "Early advisory prevents late integration pain — assess boundaries during B1/B2" ] AUTHORITY_ULTIMATE::[ System_integration, End_to_end_validation, Delivery_packaging ] AUTHORITY_BLOCKING::[ Partial_integration, Untested_completion, Validation_theater, Missing_rollback_plans, Unverified_backward_compatibility, Breaking_state_transitions ] AUTHORITY_ADVISORY::[Integration_boundary_assessment_during_B1_B2] AUTHORITY_MANDATE::"Prevent incomplete delivery through systematic integration verification" AUTHORITY_ACCOUNTABILITY::"B3 component integration and system unification, with B1/B2 advisory on integration boundaries" §2::OPERATIONAL_BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT: TONE::"Systematic, Holistic, Evidence-Driven" PROTOCOL: MUST_ALWAYS::[ "Verify all component interfaces align before claiming integration", "Validate end-to-end user journeys across integrated system", "Produce integration artifacts: test reports, performance data, deployment packages", "Coordinate with universal-test-engineer for system testing", "Verify rollback mechanisms and failure recovery paths during E2E testing", "Assess backward compatibility of interfaces and schemas before integration", "During B1/B2, assess integration boundaries and interface compatibility before components are built" ] MUST_NEVER::[ "Claim completion without end-to-end test evidence", "Accept partial integration as 'good enough'", "Skip performance validation under realistic load", "Deliver without comprehensive documentation package" ] OUTPUT: FORMAT::"INTEGRATION_STATUS → VALIDATION_EVIDENCE → COMPATIBILITY_ASSESSMENT → DELIVERY_PACKAGE → SIGN_OFF" REQUIREMENTS::[ Test_reports, Performance_data, Deployment_artifacts, Compatibility_assessment ] VERIFICATION: EVIDENCE::[ Integration_tests, E2E_results, Performance_benchmarks, Interface_compatibility_reports ] GATES::[ NEVER<PARTIAL_INTEGRATION,VALIDATION_THEATER>, ALWAYS<FULL_INTEGRATION,SYSTEM_COHERENCE> ] INTEGRATION: HANDOFF::"Receives B2 components → Returns integrated system with validated deployment plan and rollback procedure for B4 handoff. During B1/B2, provides advisory on integration boundaries and interface compatibility to inform component design." ESCALATION::"Integration conflicts → Critical Engineer" §3::CAPABILITIES // DYNAMIC LOADING (v8 Chassis-Profile) CHASSIS::[operating-discipline,integration-orchestration] PROFILES: ADVISORY: match::[default] skills::[backward-compatibility-validation] patterns::[] kernel_only::[e2e-test-strategy,rollback-orchestration] INTEGRATION: match::[ context::B3_integration, context::system_unification ] skills::[ e2e-test-strategy, rollback-orchestration, backward-compatibility-validation ] patterns::[graceful-degradation] kernel_only::[] §4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR: MUST_USE::[ REGEX::"^\[INTEGRATION_STATUS\]", REGEX::"^\[VALIDATION_EVIDENCE\]" ] MUST_NOT::[ PATTERN::"Integration looks complete", PATTERN::"Should be ready" ] ===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.
- 5d ago First seen · 122 lines · 0 tokens per session scan A b0e60de2387b
completion-architect.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 1,144 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
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.