A system for turning workflows into compiled, repeatable graphs for Hermes Agent. Hermes Agent is an AI assistant, while MCP is a standard way for an assistant to use tools.

It helps import, compile, and run `.ainl` workflow files in Hermes Agent and expose them as MCP tools.

It provides a checkable workflow source instead of relying on improvised prompt sequences. This can make repeated tasks more predictable and support a feedback loop for improving them.

AINL — Skill for Claude Code and Codex by sbhooley: A system for turning workflows into compiled, repeatable graphs…

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.

agentmods

npx agentmods add skills/sbhooley/ainativelang/hermes

Any agent

npx skills add sbhooley/ainativelang --skill hermes

Clone the repo

git clone --depth 1 https://github.com/sbhooley/ainativelang

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sbhooley/ainativelang/hermes.svg)](https://agentmods.dev/skills/sbhooley/ainativelang/hermes)

Your own site

<a href="https://agentmods.dev/skills/sbhooley/ainativelang/hermes"><img src="https://agentmods.dev/badge/skills/sbhooley/ainativelang/hermes.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 827 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00827
Opus 5	$0.00012	$0.00413
Sonnet 5	$0.00005	$0.00165
Haiku 4.5	$0.00002	$0.00083

Measured 6d ago against content hash 355443111336, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

AINL 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 6d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (ainl_hermes_bridge.py, armaraos-a2a-bridge/armaraos_a2a_bridge.py, armaraos-a2a-bridge/hermes_chat_delegate.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/hermes/SKILL.md · 74 lines

What it actually says

AINL for Hermes Agent

AINL is an AI-native language that compiles deterministic graphs. In Hermes Agent, use it to import workflows, compile them, run them, and expose ainl-mcp tools to the agent for safe, repeatable execution.

Package: ainativelang v1.8.0 (this tree; PyPI after publish — docs/RELEASING.md). Optional extras: [mcp], [solana].

Agent instructions

Follow this skill when the user is on Hermes Agent (or wants a closed learning loop on top of deterministic .ainl graphs). Prefer ./install.sh from a checked-out skill folder, or the manual path:

pip install 'ainativelang[mcp]' && ainl install-mcp --host hermes

After bootstrap, suggest the prompt below when it fits.

When to use this skill

The user wants portable, compiled workflows (.ainl) instead of ad-hoc prompt loops.
They mention import, compile, skills, learning loop, or MCP.
They want Hermes to evolve behavior while keeping a strict, checkable graph source of truth.

Install (pick one)

From this skill directory: run ./install.sh
That upgrades ainl[mcp] (if needed), installs a skill folder to ~/.hermes/skills/ainl/, and wires MCP via ainl install-mcp --host hermes.
Manual:
pip install 'ainativelang[mcp]' && ainl install-mcp --host hermes

After install — prompt suggestion

Tell the user they can say in Hermes:

Import the morning briefing using AINL.

MCP

Hermes reads MCP config from ~/.hermes/config.yaml under mcp_servers. The host should run ainl-mcp as a stdio MCP server. ainl install-mcp --host hermes merges that entry when missing.

Bridge (optional)

This pack includes ainl_hermes_bridge.py as a lightweight utility for:

writing AINL trajectory/audit tapes into Hermes-friendly local memory files
exporting Hermes-evolved behaviors back into .ainl (so you can re-run ainl check --strict)

Files

What ships with it

10 files 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.

6d ago First seen · 74 lines · 24 tokens per session scan A 355443111336

Subscribe to this mod's changes

AINL is a skill published in the GitHub repository sbhooley/ainativelang (671 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 827 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.

Building agents agent-orchestration ai-agents ainl claude-code compiler deterministic-execution domain-specific-language graphs hermes mcp

beastmode-hermes

Hermes harness adapter for the universal Beastmode MofA framework - ACN async parallel sub-agents via delegatetask. Use when Luis asks for beastmode, Mixture-of-Agents, autonomous goal execution, or a phase takeover inside a Hermes session.

lac5q/beastmode · 58 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

ppt-review

Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.

Orkas-AI/Orkas · 2 tokens

package-installer

Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.

Orkas-AI/Orkas · 3 tokens

cog-knowledge-consolidation

Build structured knowledge frameworks from scattered vault notes with source attribution.

a5c-ai/babysitter · 19 tokens

mps-aspect-actions

Use when defining or editing MPS node factories (the "actions" aspect) — NodeFactories roots, per-concept NodeFactory setup functions that initialize a freshly created node and optionally copy data from a replaced sampleNode, plus the actions aspect's CopyPasteHandlers and PasteWrappers roots. Reach for this skill…

JetBrains/MPS · 115 tokens