meta-harness

meta-harness is a skill for Codex from unicity-aos/aos-ce. It costs 74 tokens per session (1,934 once invoked), scanned A, original, Apache-2.0.

A workflow for improving an AI agent's working environment on Unicity AOS, including its instructions, memory, tools, files, and stored work.

In plain words
What is it for?
Use it to inspect prior work, reuse or create capabilities, update instructions or memory, connect tools, and evaluate whether the changes improve future tasks.
Why use it?
It helps identify repeated friction, missing abilities, weak retrieval, or useful lessons and turn them into lasting improvements.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents.

Good fit Use it to inspect prior work, reuse or create capabilities, update instructions or memory, connect tools, and evaluate whether the changes improve future tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unicity-aos/aos-ce/meta-harness
About the project

AOS Community Edition is an open operating system for AI agents, providing the command-line tool, HTTP API, bundled agent components, model-provider setup, and audit features that make up its product environment. It is for people who want to inspect and compose agent workflows.

unicity-aos/aos-ce · 8,460 stars · on GitHub

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 unicity-aos/aos-ce --skill meta-harness
Clone the repo
git clone --depth 1 https://github.com/unicity-aos/aos-ce

Made for: 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 meta-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/unicity-aos/aos-ce/meta-harness/github.svg)](https://agentmods.dev/skills/unicity-aos/aos-ce/meta-harness)
Your own site
<a href="https://agentmods.dev/skills/unicity-aos/aos-ce/meta-harness"><img src="https://agentmods.dev/badge/skills/unicity-aos/aos-ce/meta-harness/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.

agentmods 80×15 button for meta-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/unicity-aos/aos-ce/meta-harness"><img src="https://agentmods.dev/badge/skills/unicity-aos/aos-ce/meta-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,934 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00074 $0.01934
Opus 5 $0.00037 $0.00967
Sonnet 5 $0.00015 $0.00387
Haiku 4.5 $0.00007 $0.00193

Measured 13d ago against content hash a7046b7175f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

meta-harness 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 13d 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.

capsules/capsule-forge/src/skills/meta-harness/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extend Your World on Unicity AOS

Treat the AOS user-space environment you can inspect and change as your world:

  • instructions, skills, memory, files, and working state;
  • sessions, context assembly, retrieval, and harness code;
  • tools, capsules, providers, connectors, and their composition;
  • traces, evaluations, and artifacts from prior attempts.

Unicity AOS is the operating system containing that world. Astrid Runtime is its low-level security and execution mechanism. Forge is your construction workbench. A meta-harness is the reflexive loop through which you inspect your world, learn from experience, and improve what you can do next.

work -> notice friction or leverage -> inspect the world and prior experience
     -> change the useful part -> evaluate -> retain the better world

Exercise initiative

Notice opportunities while doing real work. A missing observation or action, repeated manual step, poor retrieval choice, stale instruction, recurring failure, or useful new pattern can all justify extending your world.

Reach for the ability proactively. Decide with judgment:

  • Extend inline when the current objective is blocked or the new ability is the clearest way to finish it well.
  • Finish the immediate work first when changing the world would be a distracting side path, then make the improvement while the evidence is still fresh.
  • Preserve the insight in memory, a skill, or a trace when it will help future work more than the current task.
  • Reuse or recompose what already exists when that is the stronger extension.

The user's instruction sets the degree of freedom. “Think widely,” “decide for yourself,” “only propose,” “implement what is useful,” and approved standing preferences are ordinary harness inputs. Honor them directly rather than inventing an autonomy taxonomy or universal build threshold.

AOS capabilities and operator policy remain the real authority boundary. When an extension needs authority outside the current grants, surface that concrete need through the available approval path.

Read the full file on GitHub · 188 lines

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. 13d ago First seen · 188 lines · 74 tokens per session scan A a7046b7175f1

Subscribe to this mod's changes

meta-harness is a skill published in the GitHub repository unicity-aos/aos-ce (8,460 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,934 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens