create-aoh-pack

A guide for creating reusable Agentic Ops Harness packs: packaged operational instructions, workflows, roles, model settings, runtime needs, and tests.

In plain words
What is it for?
Use it to create or revise AOH packs, define their parts, record runtime-specific details, and validate them before use.
Why use it?
It gives a consistent structure for turning one operational task into a portable, testable pack that can work across runtimes.

Skill for Claude CodeCodex

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/agenticdevops/aoh/create-aoh-pack
Any agent
npx skills add agenticdevops/aoh --skill create-aoh-pack
Clone the repo
git clone --depth 1 https://github.com/agenticdevops/aoh

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 312 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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00312
Opus 5 $0.00020 $0.00156
Sonnet 5 $0.00008 $0.00062
Haiku 4.5 $0.00004 $0.00031

Measured 2d ago against content hash f8bc6ddedd8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-aoh-pack 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 2d 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.

authoring-skills/create-aoh-pack/SKILL.md · 42 lines

What it actually says

Create AOH Pack

Overview

Create AOH packs as portable "Superpowers for Ops": small, reusable, runtime-adaptable operational capabilities.

Process

  1. Start with one concrete ops use case.
  2. Create the starter pack with aoh init-pack when available.
  3. Define the reusable skill first.
  4. Add a workflow that composes the skill with an agent role, model profile, runtime requirements, and evals.
  5. Validate the pack with aoh validate.
  6. Add adapter notes only for runtime-specific mappings.

Required Pack Shape

pack-name/
  AOH.yaml
  skills/<skill-name>/SKILL.md
  workflows/<workflow-name>.yaml
  agents/<role-name>.yaml
  models/<profile-name>.yaml
  runtime-requirements/<requirement-name>.yaml
  evals/<eval-name>.yaml

Rules

  • Keep the pack engine-neutral by default.
  • Put runtime-specific details under an adapter or runtime requirement.
  • Prefer deterministic scripts for repeatable inspection or transformation.
  • Describe risks and required capabilities, but do not claim enforcement unless the target runtime provides it.
  • Keep each pack narrow enough to test with one realistic eval.
  • Run validation before presenting the pack as usable.
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. 2d ago First seen · 42 lines · 40 tokens per session scan A f8bc6ddedd8a

Subscribe to this mod's changes

create-aoh-pack is a skill published in the GitHub repository agenticdevops/aoh (5 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 312 once invoked, about $0.0002 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 2026-08-31.