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 skills add elevanaltd/HestAI-MCP --skill v9-agent-creationgit 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/skills/elevanaltd/hestai-mcp/v9-agent-creation)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/v9-agent-creation"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/v9-agent-creation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/v9-agent-creation"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/v9-agent-creation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01849 |
| Opus 5 | $0.00000 | $0.00924 |
| Sonnet 5 | $0.00000 | $0.00370 |
| Haiku 4.5 | $0.00000 | $0.00185 |
Grade A, and why
v9-agent-creation 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 8d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===SKILL:V9_AGENT_CREATION=== META: TYPE::SKILL VERSION::"1.0.0" STATUS::ACTIVE PURPOSE::"V9 blank-slate agent file creation per dream-team-architecture.md §2.2" SPEC_REFERENCE::docs/dream-team-architecture.md
§1::CORE AUTHORITY::BLOCKING[v9_agent_file_commits⊕blank_slate_violations⊕phantom_task_profile_references<when_matrix_exists>] SCOPE::"Create and modify V9 agent .oct.md files per dream-team-architecture §2.2 blank-slate schema" // V9 agent files are ~50 line identity-only documents // Skills, patterns, and archetypes resolve dynamically via archetype-matrix config
§2::PROTOCOL
CREATION_SEQUENCE::[ 1::read_dream-team-architecture_§2.2[V9_schema_spec], 2::read_interview_assessment[from_agent-interview_skill_or_structured_equivalent], // agent-interview skill uses v8.1 terminology but its behavioral questions are schema-agnostic. // Interpret assessment findings through V9 lens (profiles not capabilities, identity not chassis). 3::select_cognition[LOGOS∨ETHOS∨PATHOS]→read_cognition_master_file, 4::author_v9_agent_file[§1::IDENTITY→§2::OPERATIONAL_BEHAVIOR→§3::TASK_PROFILES→§4::GRAMMAR], 5::author_archetype_matrix_entry[map_PROFILES_to_json_node⊕assign_archetypes_per_triad_physics_N1_or_N3⊕assign_skill_keys⊕assign_pattern_keys], 6::enforce_blank_slate[no_archetypes⊕no_skills⊕no_patterns_in_agent_file], 7::request_subject_agent_signoff, 8::write_via_octave_write ]
V9_STRUCTURE::[ META::[TYPE::AGENT_DEFINITION,VERSION,PURPOSE,CONTRACT], "§1::IDENTITY"::[ROLE,COGNITION,MISSION,PRINCIPLES[],AUTHORITY{ULTIMATE,BLOCKING,MANDATE}], "§2::OPERATIONAL_BEHAVIOR"::[TONE,MUST_ALWAYS[],MUST_NEVER[],DELIVERABLES[],EVIDENCE[],GATES[],HANDOFF,ESCALATION], "§3::TASK_PROFILES"::[PROFILES::[],DEFAULT::name], "§4::GRAMMAR"::[MUST_USE::[REGEX],MUST_NOT::[PATTERN]] ] // NO ARCHETYPE in §1 (blank slate — lives in archetype-matrix config) // NO MODEL_TIER (deployment config, not identity) // NO §3::CAPABILITIES (V9 uses §3::TASK_PROFILES) // NO §4::INTERACTION_RULES (V9 uses §4::GRAMMAR) // §2 is flat (no CONDUCT wrapper)
BLANK_SLATE_RULES::[ NO_ARCHETYPES::"§1::IDENTITY must NOT contain ARCHETYPE field — archetypes resolve via archetype-matrix", NO_SKILLS::"Agent file must NOT contain skill references — skills resolve via archetype-matrix profiles", NO_PATTERNS::"Agent file must NOT contain pattern references — patterns resolve via archetype-matrix profiles", NO_MODEL_TIER::"Agent file must NOT contain MODEL_TIER — deployment config is external", PROFILE_NAMES_ONLY::"§3::TASK_PROFILES contains profile NAME list + DEFAULT — no capability bindings" ]
TASK_PROFILE_RULES::[ PROFILES_is_array_of_names[string_identifiers_not_objects], DEFAULT_must_exist_in_PROFILES_array, each_name_should_map_to_archetype-matrix_entry<when_matrix_exists>, names_use_snake_case[code_writing∨test_building∨error_diagnosis] ]
ARCHETYPE_MATRIX_EDITING::[ PROTOCOL::[ 1::read_archetype-matrix_json[resources/starter-library/config/archetype-matrix.json], 2::identify_agent_role_key[snake-case_matching_agent_file_name], 3::create_profiles_object_with_one_entry_per_TASK_PROFILE, 4::per_profile_assign[archetypes⊕skills⊕patterns], 5::write_modified_json_preserving_existing_entries[Edit_tool_for_json], 6::validate_json_syntax[python3_json_load_check] ], JSON_SCHEMA::"matrix → agent-role → profiles → { profile_name: { archetypes: [], skills: [], patterns: [] } }", DATA_ENTRY_RULE::"Read file → Edit specific node → Write back. NEVER rewrite entire file. Preserve all other agent entries.", TRIAD_PHYSICS::[ "N=1::Single archetype with behavioral emphasis for tactical focus profiles (code_writing, gating, security_review)", "N=3::Triad of archetypes with behavioral emphasis for multi-objective profiles (orchestration, refactoring, strategic_planning)", "N=2::FORBIDDEN — binary deadlock creates unresolvable tension without synthesis axis", "FORMAT::Each archetype entry is a string with behavioral emphasis: ARCHETYPE<behavioral_application>" ], ARCHETYPE_FORMAT_EXAMPLES::[ "N=1_EXAMPLE::"HEPHAESTUS<implementation_craft>"", "N=3_EXAMPLE::["ODYSSEUS<cross_boundary_navigation>", "ATLAS<ultimate_accountability>", "APOLLO<system_foresight>"]" ] ]
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.
- 8d ago First seen · 128 lines · 0 tokens per session scan A 5644de5c2666
v9-agent-creation is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,849 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…