autostar

autostar is a skill for Claude Code, Codex from chrisvoncsefalvay/autostar. It costs 183 tokens per session (6,291 once invoked), scanned A, original, MIT.

A general method for improving something through repeated experiments, measurement, reflection, and adjustment. It can be applied to code, prompts, documents, settings, designs, or other work that has a measurable goal.

In plain words
What is it for?
It helps define an objective, run experiments, evaluate several aspects of the output, reflect at checkpoints, and use earlier results to guide later attempts.
Why use it?
It provides a structured way to compare attempts and learn which changes improve the result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Good fit It helps define an objective, run experiments, evaluate several aspects of the output, reflect at checkpoints, and use earlier results to guide later attempts.

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

Made for: Claude Code, 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 autostar

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisvoncsefalvay/autostar/autostar-skill/github.svg)](https://agentmods.dev/skills/chrisvoncsefalvay/autostar/autostar-skill)
Your own site
<a href="https://agentmods.dev/skills/chrisvoncsefalvay/autostar/autostar-skill"><img src="https://agentmods.dev/badge/skills/chrisvoncsefalvay/autostar/autostar-skill/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 autostar

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrisvoncsefalvay/autostar/autostar-skill"><img src="https://agentmods.dev/badge/skills/chrisvoncsefalvay/autostar/autostar-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,291 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 $0.00183 $0.06291
Opus 5 $0.00092 $0.03145
Sonnet 5 $0.00037 $0.01258
Haiku 4.5 $0.00018 $0.00629

Measured 11d ago against content hash 51513c013ef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

autostar 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 11d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/__init__.py, scripts/memory_backend.py, scripts/memory_cli.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.

autostar-skill/SKILL.md · 645 lines

How it starts

The opening of the file, as written. The whole thing — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.

a* (autostar)

A generalised autonomous optimisation loop — soft RLVR for the masses. The user defines a goal; the system runs structured experiments, evaluates progress across independent tracks, reflects at strategic checkpoints, and learns from every attempt — including learning how to learn better the next time.

If you can measure it, you can improve it.


Experimental-first principle

a* is an experimental optimisation loop. Do not reach for external mathematical optimisers or solvers (e.g. scipy.optimize, cvxpy, linear/quadratic programming solvers, evolutionary algorithm libraries, Bayesian optimisation frameworks, or any other off-the-shelf optimisation package) as a shortcut to improving the artifact. The value of a* is in the structured explore-evaluate-reflect cycle, not in delegating the search to a solver.

If at any point during onboarding, pre-run analysis, or execution you believe the problem is well-suited to a closed-form or mathematical optimisation approach, you must ask the user first before pursuing it. Present it as an alternative:

"This problem looks like it could be approached with a mathematical optimiser (e.g. [specific method]). Would you like me to try that instead of running the experimental loop, or would you prefer to proceed with a*?"

Do not silently install, import, or invoke an external optimiser. Do not reframe the a* loop as a wrapper around a solver. If the user explicitly opts for a mathematical approach, that is a different workflow — not an a* run.


Concepts

Before running, ensure you understand these terms precisely:

Term Meaning
Step One execution with one parameter set. Atomic unit of work.
Play A named bundle of parameters that move together (optional; disable with plays: false).
Lap A set of steps sharing the same parameter family. Establishes statistical confidence in a direction.
Round A set of laps. Ends with a mandatory reflection: worth pursuing? ask user? pivot?
Run One user-initiated process. Lasts until budget is exhausted or goal is met.
Track One independently verifiable sub-goal. Has its own verifier and ratchet.
Disposition A learned prior on how to approach a (problem class, action intent) pair. Stored in long-term memory; conditions all significant actions.

Read the full file on GitHub · 645 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. 11d ago First seen · 645 lines · 183 tokens per session scan A 51513c013ef8

Subscribe to this mod's changes

autostar is a skill published in the GitHub repository chrisvoncsefalvay/autostar (39 stars, last pushed 5mo ago), licensed MIT. It adds 183 tokens to every session and 6,291 once invoked, about $0.0009 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

autoresearch

Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. Supports optional loop count via Claude Code's /loop command. Invoking /autoresearch builds a real-data benchmark harness, captures a baseline, and iterates with a…

Muminur/autoresearch-skill-Andrej-Karpathy · 82 tokens

vox-director

Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…

Alisa0808/vox-director · 236 tokens

social-post

A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.

Hao0321/claude-skill-social-post · 135 tokens

grid-ctf-ops

Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.

greyhaven-ai/autocontext · 42 tokens

os-whats-next

ALWAYS invoke this skill when the user asks what to do next, what is left, or what is blocked - "what's next", "what now", "what should we work on", "anything I can do" - in any language. This skill picks the next piece of work; when the user asks HOW to do a thing or says they do not understand what to do, that is…

kharmanskyi/open-steps · 155 tokens

higgsfield-troubleshoot

Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.

OSideMedia/higgsfield-ai-prompt-skill · 39 tokens