hyperagent

hyperagent is a skill for Claude Code from ckorhonen/claude-skills. It costs 84 tokens per session (3,127 once invoked), scanned A, original, MIT.

A self-improvement loop in which one software agent changes another agent or program, measures the result, and keeps improvements that score better.

In plain words
What is it for?
Use it to optimize scripts for speed, improve prompts for accuracy, or evolve functions and other Python programs through repeated benchmarked changes.
Why use it?
It helps test repeated changes against a measurable target instead of relying only on human judgment about whether code or prompts improved.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../hyperagent-<goal>-<date> -b hyperagent/<goal>-<date>.

Part of the claude-skills plugin — 62 skills, 4 commands, 7 agents shipped together

Good fit Use it to optimize scripts for speed, improve prompts for accuracy, or evolve functions and other Python programs through repeated benchmarked changes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ckorhonen/claude-skills
agentmods
npx agentmods add skills/ckorhonen/claude-skills/hyperagent

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 7 agents.

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 hyperagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/claude-skills/hyperagent.svg)](https://agentmods.dev/skills/ckorhonen/claude-skills/hyperagent)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/hyperagent"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/hyperagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,127 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 $0.00084 $0.03127
Opus 5 $0.00042 $0.01563
Sonnet 5 $0.00017 $0.00625
Haiku 4.5 $0.00008 $0.00313

Measured 8d ago against content hash b882ba44a410, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hyperagent 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 8d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (scripts/common.py, scripts/init_session.py, scripts/log_variant.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/hyperagent/SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hyperagent

Quick Start — Simple Examples

New to Hyperagent? Try these beginner-friendly tasks before the full setup.

1. Optimize a simple Python script to run faster

Say: "Use hyperagent to optimize this script for speed" and paste something like:

# slow_sort.py
def sort_numbers(nums):
    result = []
    while nums:
        smallest = min(nums)
        result.append(smallest)
        nums.remove(smallest)
    return result

Hyperagent will benchmark it, propose a faster implementation, and validate the improvement.

2. Improve a prompt to get better answers

Say: "Run hyperagent on this prompt and improve accuracy" with a prompt like:

Summarize this article in one sentence.

The meta-agent iterates on the prompt, measures quality, and keeps improvements that score higher.

3. Make a sorting function more efficient

Say: "Evolve this function with hyperagent" and paste any function. Hyperagent creates a benchmark, runs generations of improvements, and shows you the performance gain per generation.

4. Self-improve any script

Say: "Self-improve this agent/script" and point to any Python file. Hyperagent wraps it in an evaluation loop, proposes modifications, and tracks what works.

The simplest possible setup: create task.sh that prints METRIC score=0.5, then run python3 scripts/init_session.py. From there the loop is fully automated.


Self-referential self-improvement: a meta-agent that modifies a task-agent (and itself) to optimize any measurable objective.

Inspired by Facebook Research's Hyperagents paper (arXiv:2603.19461), which demonstrated that agents combining a task-solver and a self-modifying meta-level into a single editable program can achieve open-ended, compounding improvements that transfer across domains.

How It Works

A hyperagent is a system with two components in a single editable codebase:

  1. Task Agent — solves the target task (benchmark, code generation, data processing, etc.)
  2. Meta Agent — analyzes task performance history and proposes modifications to the task agent's code (and optionally its own code)

Read the full file on GitHub · 369 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. 8d ago First seen · 369 lines · 84 tokens per session scan A b882ba44a410

Subscribe to this mod's changes

hyperagent is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 3,127 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

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

huggingface-llm-trainer

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

waybarrios/opencode-power-pack · 65 tokens

feature-dev

Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…

waybarrios/opencode-power-pack · 62 tokens