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.
npx skills add kcdjmaxx/HomarUScc --skill autoresearchgit clone --depth 1 https://github.com/kcdjmaxx/HomarUSccWrote 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/kcdjmaxx/homaruscc/autoresearch)<a href="https://agentmods.dev/skills/kcdjmaxx/homaruscc/autoresearch"><img src="https://agentmods.dev/badge/skills/kcdjmaxx/homaruscc/autoresearch.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.02954 |
| Opus 5 | $0.00035 | $0.01477 |
| Sonnet 5 | $0.00014 | $0.00591 |
| Haiku 4.5 | $0.00007 | $0.00295 |
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoresearch
Autonomous experimentation loop that iteratively improves a target file by forming hypotheses, making changes, evaluating results, and keeping only what works. The human "programs" the agent by writing a program.md file that describes the research direction.
Usage
/autoresearch -- start the experiment loop using ./program.md
/autoresearch --resume -- resume from where the last session left off
/autoresearch --status -- show experiment history and current baseline
/autoresearch --dry-run -- parse program.md and show config without running
Prerequisites
The current working directory must contain a program.md file. This file is the human's instruction document -- it tells the agent what to optimize, how to evaluate, and what strategies to explore. See the "program.md Format" section below for the required structure.
How It Works
Step 1: Parse program.md
Read program.md from the current working directory. Extract the configuration block (YAML fenced block near the top) and the research direction prose.
Required configuration fields:
target_file: train.py # The single file the agent modifies
eval_command: python train.py # Command that runs the experiment
metric_key: val_loss # JSON key to extract from eval output
direction: minimize # "minimize" or "maximize"
max_experiments: 50 # Stop after this many experiments
experiment_timeout: 300 # Max seconds per experiment run
Optional configuration fields:
baseline_command: null # If set, run this once to establish baseline (otherwise first eval_command run is baseline)
metric_format: json_stdout # "json_stdout" (default), "json_file:<path>", or "last_line"
git_branch: autoresearch # Branch name for experiments (default: autoresearch/<timestamp>)
preserve_on_fail: false # If true, don't revert failed experiments (for debugging)
cooldown_seconds: 5 # Pause between experiments (default: 5)
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.
- 7d ago First seen · 335 lines · 70 tokens per session scan A 9ae395d1da7d
autoresearch is a skill published in the GitHub repository kcdjmaxx/HomarUScc (1 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 2,954 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…