harness_portability

harness_portability is a skill for Claude Code from theafh/ai-modules. It costs 157 tokens per session (4,762 once invoked), scanned A, original, MIT.

A review guide for making scripts, hooks, commands, servers, and setup files work across different coding-agent systems and operating systems.

In plain words
What is it for?
Use it when creating, editing, reviewing, or troubleshooting portable skill and plugin scripts, hooks, wrappers, installation flows, and related instructions.
Why use it?
It helps prevent runtime artifacts from depending on one machine, shell, agent harness, or unverified configuration detail.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Codex; mentions Gemini CLI.

Part of the ai_dev plugin — 24 skills, 5 agents, 1 hook shipped together

Good fit Use it when creating, editing, reviewing, or troubleshooting portable skill and plugin scripts, hooks, wrappers, installation flows, and related instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/theafh/ai-modules/harness_portability
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 theafh/ai-modules --skill harness_portability
Clone the repo
git clone --depth 1 https://github.com/theafh/ai-modules

Made for: Claude Code.

Or install ai_dev, the plugin that ships this one along with the rest of its 24 skills, 5 agents, 1 hook.

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 harness_portability

README.md
[![agentmods](https://agentmods.dev/badge/skills/theafh/ai-modules/harness_portability.svg)](https://agentmods.dev/skills/theafh/ai-modules/harness_portability)
Your own site
<a href="https://agentmods.dev/skills/theafh/ai-modules/harness_portability"><img src="https://agentmods.dev/badge/skills/theafh/ai-modules/harness_portability.svg" alt="Measured on agentmods" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,762 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 $0.00157 $0.04762
Opus 5 $0.00078 $0.02381
Sonnet 5 $0.00031 $0.00952
Haiku 4.5 $0.00016 $0.00476

Measured 7d ago against content hash b30c12713214, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

harness_portability 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.

plugins/ai_dev/skills/harness_portability/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harness_portability

<harness_portability> Keep bundled skill and plugin runtime artefacts portable across agent harnesses and operating systems. Apply this skill whenever a change creates or edits scripts, hooks, agent definitions, MCP helpers, command wrappers, setup flows, output styles, or the skill and plugin wording that tells future agents how to execute, initialize, or configure those artefacts.

<fact_sourcing> <verify_before_encoding> Treat every concrete harness fact as perishable: a configuration root, a frontmatter key, a tool name, an environment variable, a hook event, a settings key, a version threshold. Confirm each one against current official provider documentation, the loader source, or the installed build before a change depends on it, and record which of those three the claim rests on. An observed behavior on the machine at hand outranks documentation that omits it, and documentation outranks recollection. </verify_before_encoding> <where_snapshots_live> Where the working repository carries a wiki, read its harness pages first: they hold the last verified snapshot with the date and source behind each claim, which makes them a starting point that still needs re-verification rather than an authority. Write a new finding back there, or into this skill's own references/ directory when a future agent needs it in a repository that has no such wiki. Keep this skill body to the rules themselves, so a portability review costs the rules rather than the whole fact base. </where_snapshots_live> <state_the_gap> State the verification gap plainly when a claim could not be confirmed, and name what would settle it. Carry an unconfirmed classification as pending rather than resolving it toward whichever answer is convenient, because a wrong negative closes a line of inquiry that a stated gap keeps open. </state_the_gap> </fact_sourcing>

Read the full file on GitHub · 127 lines

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 · 127 lines · 157 tokens per session scan A b30c12713214

Subscribe to this mod's changes

harness_portability is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 4,762 once invoked, about $0.0008 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.