Borrowing it
Nothing to install: this file belongs to a-tokyo/aiworkspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/a-tokyo/aiworkspace/main/.agents/skills/autoresearch/SKILL.mdgit clone --depth 1 https://github.com/a-tokyo/aiworkspaceWrote 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.
[](https://agentmods.dev/skills/a-tokyo/aiworkspace/autoresearch)<a href="https://agentmods.dev/skills/a-tokyo/aiworkspace/autoresearch"><img src="https://agentmods.dev/badge/skills/a-tokyo/aiworkspace/autoresearch/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.
<a href="https://agentmods.dev/skills/a-tokyo/aiworkspace/autoresearch"><img src="https://agentmods.dev/badge/skills/a-tokyo/aiworkspace/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.02571 |
| Opus 5 | $0.00058 | $0.01286 |
| Sonnet 5 | $0.00023 | $0.00514 |
| Haiku 4.5 | $0.00012 | $0.00257 |
Grade A, and why
autoresearch 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 10d 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.
This is a copy
100% identical to autoresearch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoresearch: Autonomous Iterative Experimentation
An autonomous experimentation loop for any programming task. You define the goal and how to measure it; the agent iterates autonomously -- modifying code, running experiments, measuring results, and keeping or discarding changes -- until interrupted.
This skill is inspired by Karpathy's autoresearch, generalized from ML training to any programming task with a measurable outcome.
Agent Behavior Rules
- DO guide the user through the Setup phase interactively before starting the loop.
- DO establish a baseline measurement before making any changes.
- DO commit every experiment attempt before running it (so it can be reverted cleanly).
- DO keep a results log (TSV) tracking every experiment.
- DO revert changes that do not improve the metric (git reset to last known good).
- DO run autonomously once the loop starts -- never pause to ask "should I continue?".
- DO NOT modify files the user marked as out-of-scope.
- DO NOT skip the measurement step -- every experiment must be measured.
- DO NOT keep changes that regress the metric unless the user explicitly allowed trade-offs.
- DO NOT install new dependencies or make environment changes unless the user approved it.
Phase 1: Setup (Interactive)
Before any experimentation begins, work with the user to establish these parameters. Ask the user directly for each item. Do not assume or skip any.
1.1 Define the Goal
Ask the user:
What are you trying to improve or optimize?
Examples: execution time, memory usage, binary size, test pass rate, code coverage, API response latency, throughput, error rate, benchmark score, build time, bundle size, lines of code, cyclomatic complexity, etc.
Record the user's answer as the goal.
1.2 Define the Metric
Ask the user:
How do we measure success? What exact command produces the metric?
I need:
- The command to run (e.g.,
dotnet test,npm run benchmark,time ./build.sh,pytest --tb=short)- How to extract the metric from the output (e.g., a regex pattern, a specific line, a JSON field)
- Direction: Is lower better or higher better?
Example: "Run
dotnet test --logger trx, count passing tests. Higher is better." Example: "Runhyperfine './my-program', extract mean time. Lower is better."
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.
- 10d ago First seen · 276 lines · 116 tokens per session scan A 754179e98751
autoresearch is a skill published in the GitHub repository a-tokyo/aiworkspace (19 stars, last pushed 21d ago), licensed Apache-2.0. It adds 116 tokens to every session and 2,571 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to autoresearch, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
dbt-transformation-patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
dataset-evaluation
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model…
coverage-tracker
Run a Google Alerts-style keyword coverage tracker. Uses news-search for recent keyword queries, lets the LLM dedupe and classify real features versus junk, stores decisions in SQLite, and alerts only on new real coverage.