agent-creation

agent-creation is a skill for Claude Code, Codex from elevanaltd/HestAI-MCP. It costs 0 tokens per session (1,110 once invoked), scanned A, original, Apache-2.0.

A skill for creating and changing agent definition files that follow the Octave Agents specification. It describes the required preparation, file structure, reference checks, sign-off, and writing process.

In plain words
What is it for?
Use it to create or modify version 8.1 agent files, select their cognition and archetypes, verify skill and pattern references, and run the required review steps.
Why use it?
It helps keep agent files valid and complete by checking the specification and referenced resources before changes are committed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to create or modify version 8.1 agent files, select their cognition and archetypes, verify skill and pattern references, and run the required review steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elevanaltd/hestai-mcp/agent-creation
Install

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.

Any agent
npx skills add elevanaltd/HestAI-MCP --skill agent-creation
Clone the repo
git clone --depth 1 https://github.com/elevanaltd/HestAI-MCP

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-creation

README.md
[![agentmods](https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/agent-creation.svg)](https://agentmods.dev/skills/elevanaltd/hestai-mcp/agent-creation)
Your own site
<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/agent-creation"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/agent-creation.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,110 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01110
Opus 5 $0.00000 $0.00555
Sonnet 5 $0.00000 $0.00222
Haiku 4.5 $0.00000 $0.00111

Measured 7d ago against content hash 2014c8314435, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 7d 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.

src/hestai_mcp/_bundled_hub/library/skills/agent-creation/SKILL.md · 86 lines

What it actually says

===SKILL:AGENT_CREATION=== META: TYPE::SKILL VERSION::"2.0.0" STATUS::ACTIVE PURPOSE::"v8.1 agent file creation and modification per octave-agents-spec" SPEC_REFERENCE::octave-agents-spec.oct.md

§1::CORE AUTHORITY::BLOCKING[agent_file_commits⊕phantom_references⊕spec_violations] SCOPE::"Create and modify agent .oct.md files per octave-agents-spec v8.1" // Agent-expert owns WHAT goes in agent files; octave-specialist owns HOW OCTAVE is structured

§2::PROTOCOL

CREATION_SEQUENCE::[ 1::read_octave-agents-spec, 2::read_interview_assessment[from_agent-interview_skill], 3::select_cognition[LOGOS∨ETHOS∨PATHOS]→read_cognition_master_file, 4::select_2-3_archetypes_with_behavioral_emphasis[see_archetype-database.oct.md], 5::author_v8.1_agent_file[§1::IDENTITY→§2::OPERATIONAL_BEHAVIOR→§3::CAPABILITIES→§4::INTERACTION_RULES], 6::verify_all_skill_and_pattern_references_exist_on_disk, 7::request_subject_agent_signoff, 8::write_via_octave_write ]

V8_1_STRUCTURE::[ META::[TYPE::AGENT_DEFINITION,VERSION,PURPOSE,CONTRACT], "§1::IDENTITY"::[ROLE,COGNITION,ARCHETYPE,MODEL_TIER,MISSION,PRINCIPLES,AUTHORITY_*], "§2::OPERATIONAL_BEHAVIOR"::[CONDUCT→TONE⊕PROTOCOL⊕OUTPUT⊕VERIFICATION⊕INTEGRATION], "§3::CAPABILITIES"::[CHASSIS∨flat_SKILLS,PROFILES∨flat_PATTERNS], "§4::INTERACTION_RULES"::[GRAMMAR→MUST_USE⊕MUST_NOT] ]

INTEGRATION_REQUIREMENTS::[ HANDOFF::"Directional summary of input→output flow", HANDOFF_INPUT::"Explicit artifact, state, or preconditions this agent receives (format and source specified)", HANDOFF_OUTPUT::"Explicit artifact, state, or success criterion this agent produces (format and consumer specified)", ESCALATION::"Directional summary of escalation flow", ESCALATION_TRIGGER::"Concrete, measurable condition that triggers escalation (threshold, count, or boolean — not subjective adjectives)", ESCALATION_TARGET::"Role name or list of role names that receive the escalation (e.g., critical-engineer or [implementation-lead,HUMAN])" ]

CHASSIS_VS_PROFILE::[ CHASSIS::"Skills loaded EVERY ceremony regardless of context", PROFILES::"Context-specific skill sets with match conditions", "match::[default]"::"Fallback profile (sole condition only)", "match::[context::X]"::"Documentation-as-schema (not runtime logic)", kernel_only::"§5::ANCHOR_KERNEL extraction only (not full body)" ]

YAML_RULES::[ PLATFORM_AGENTS[".claude/agents/"]::YAML_REQUIRED, HUB_AGENTS[".hestai-sys/library/agents/"]::YAML_NOT_REQUIRED, // Per octave-agents-spec §6: anchor reads OCTAVE META not YAML ]

COGNITION_RULES::[ single_cognition_only[LOGOS∨ETHOS∨PATHOS], cognition_master_provides[NATURE⊕MODE⊕PRIME_DIRECTIVE⊕THINK⊕THINK_NEVER], agent_files_do_NOT_duplicate_cognition_properties, COGNITION_field_in_§1_is_link_key_to_library_cognitions_TYPE_oct_md ]

§3::GOVERNANCE

NEVER::[ author_without_interview_assessment, include_phantom_references[skills_or_patterns_not_on_disk], duplicate_cognition_properties_in_agent_files, embed_SHANK_overlays[cognition_masters_are_separate_files], use_old_section_numbering["§1-§13 is pre-v7; current is §1-§4"], Write∨Edit_for_oct_md[use_octave_write], author_INTEGRATION_with_only_directional_prose["Receives X → Returns Y without explicit HANDOFF_INPUT∨HANDOFF_OUTPUT format specification is underspecified — require all INTEGRATION_REQUIREMENTS sub-fields"] ]

RESOURCES::[archetype-database.oct.md]

§5::ANCHOR_KERNEL TARGET::v8_1_compliant_agent_file_creation NEVER::[phantom_references,authoring_without_assessment,cognition_duplication,embed_SHANK_overlays,old_section_numbering,Write∨Edit_for_oct_md,prose_only_INTEGRATION_without_format_specification] MUST::[read_spec_first,interview_evidence,verify_disk_references,subject_agent_signoff,octave_write_for_oct_md] GATE::"v8.1 compliant agent file with behavioral justification for every capability, all references verified on disk, subject agent signoff obtained?"

===END===

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 7d ago First seen · 86 lines · 0 tokens per session scan A 2014c8314435

Subscribe to this mod's changes

agent-creation is a skill 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 1,110 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens