meta-harness

meta-harness is a skill for Claude Code, Codex from 001TMF/harness-forge. It costs 217 tokens per session (2,181 once invoked), scanned A, original, MIT.

A method for improving the supporting code around a fixed AI model. It tests different ways to store, retrieve, shorten, and present information, then compares their quality and cost.

In plain words
What is it for?
Use it to experiment with memory, search results, context building, prompts, summaries, or tool-selection rules. It can keep the best trade-offs between answer quality and running cost.
Why use it?
It helps find better ways to run an AI system without changing the model itself. A cheap, repeatable evaluation makes it easier to compare many possible setups.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to experiment with memory, search results, context building, prompts, summaries, or tool-selection rules. It can keep the best trade-offs between answer quality and running cost.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/001tmf/harness-forge/meta-harness
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 001TMF/harness-forge --skill meta-harness
Clone the repo
git clone --depth 1 https://github.com/001TMF/harness-forge

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin harness-forge/plugin install harness-forge after adding the marketplace above.

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/001tmf/harness-forge/meta-harness.svg)](https://agentmods.dev/skills/001tmf/harness-forge/meta-harness)
Your own site
<a href="https://agentmods.dev/skills/001tmf/harness-forge/meta-harness"><img src="https://agentmods.dev/badge/skills/001tmf/harness-forge/meta-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 217 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,181 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 $0.00217 $0.02181
Opus 5 $0.00109 $0.01091
Sonnet 5 $0.00043 $0.00436
Haiku 4.5 $0.00022 $0.00218

Measured 7d ago against content hash a627e30cae45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (assets/candidate_base-template.py, assets/scorer-template.py, assets/workflow-template.js, …), 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/meta-harness/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Harness (native)

What this is

Meta-Harness optimizes the harness, not the model. The harness is the code around a fixed base model that decides what to store, retrieve, compress, and show while the model works. You hold the model frozen and search over that scaffolding: propose candidate variants, score each on a cheap deterministic eval, keep a Pareto frontier (quality up, cost down), and iterate. The proposer is an LLM agent writing code; the inner loop is a cheap scorer.

The Stanford repo (stanford-iris-lab/meta-harness) ships a Python driver — claude_wrapper.py (~720 lines) + meta_harness.py (~540 lines) — that reimplements an agent runtime to drive a headless Claude: spawn a session, parse stream-json, track tool calls, log everything, loop. You already are that runtime. So you run the same loop with native tools (Agent, Workflow, /loop) and keep only the irreducible domain logic — a $0 scorer. The orchestration was never the hard part; your harness provides it.

This skill is the method, reusable for any harness-optimization task. A fully worked example (optimizing proteus's campaign-memory summarizer) lives at ~/mh-proteus/ and is walked through in references/proteus-example.md.

When to use this

Strong fit when several of these hold (full criteria in references/method.md):

  • The base model is fixed and the opportunity is better retrieval / memory / context / prompting / tool scaffolding. (This is the whole premise — if the gain must come from the model weights, this is the wrong tool: do RL/fine-tuning instead.)
  • There are repeated episodes / tasks, not a one-off.
  • There is a cheap, deterministic eval with a real success signal — or you can build one.
  • The search set is large enough to expose failure modes, small enough to iterate.
  • There are recurring error patterns a harness could fix systematically.

Poor fit: no stable eval loop, or purely subjective quality with no measurable criterion.

Read the full file on GitHub · 148 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 · 148 lines · 217 tokens per session scan A a627e30cae45

Subscribe to this mod's changes

meta-harness is a skill published in the GitHub repository 001TMF/harness-forge (77 stars, last pushed 2mo ago), licensed MIT. It adds 217 tokens to every session and 2,181 once invoked, about $0.0011 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

llm-integration

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

yonatangross/orchestkit · 58 tokens

prompt-enhancer

Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…

sammcj/agentic-coding · 67 tokens

llm-prompting-guide

Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…

sammcj/agentic-coding · 79 tokens

llm-prompting

Write effective LLM prompts — role framing, few-shot examples, constraints, system/user placement, and a repeatable evaluation loop.

vikasudasi/skill-vault · 32 tokens

ai-native-development

Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.

ArieGoldkin/ai-agent-hub · 48 tokens

prompt-engineering

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

wpank/ai · 44 tokens