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 jdrhyne/agent-skills --skill autoresearch-loopgit clone --depth 1 https://github.com/jdrhyne/agent-skillsWrote 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/jdrhyne/agent-skills/autoresearch-loop)<a href="https://agentmods.dev/skills/jdrhyne/agent-skills/autoresearch-loop"><img src="https://agentmods.dev/badge/skills/jdrhyne/agent-skills/autoresearch-loop/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/jdrhyne/agent-skills/autoresearch-loop"><img src="https://agentmods.dev/badge/skills/jdrhyne/agent-skills/autoresearch-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.01857 |
| Opus 5.5 | $0.00048 | $0.00743 |
| Sonnet 5.5 | $0.00024 | $0.00371 |
| Haiku 4.5 | $0.00012 | $0.00186 |
Grade A, and why
autoresearch-loop 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoresearch-loop
Generalize Karpathy's autoresearch into a domain-adaptive improvement loop. The agent discovers what to measure, then runs a disciplined propose → trial → keep-or-revert loop, maintaining an explicit ledger of what was tried, kept, discarded, and implemented.
Read DESIGN.md once at the start of a run for the full architecture and the domain-specific tensions (metric latency/noise/cost, Goodhart gaming, cost-per-trial, reversibility). The phases below are the operating procedure.
Runtime: the loop's mechanics (run a trial, parse the metric, score confidence, keep/commit or discard/revert) are handled by the arl CLI over a .auto/ session folder — a Claude-native port of pi-autoresearch's tools. Read references/runtime-contract.md for the .auto/ layout, the METRIC name=value contract, MAD confidence scoring, and the arl init|run|log|status commands. Invoke it as node scripts/arl.mjs <cmd> (or arl if on PATH).
When NOT to run
- There is no metric that can be measured repeatably and cheaply enough within a trial budget. A loop with no trustworthy metric chases noise — stop and say so.
- The change surface is irreversible or unsafe to mutate experimentally (production data, customer-facing irreversible actions) without an explicit revert procedure in the adapter.
Phase 0 — FRAME (metric discovery)
Given {project, goal, context} — follow the procedure in references/metric-discovery.md (restate the goal as an outcome → enumerate candidates on the proxy→outcome spectrum → score on six axes → choose primary + guardrails + strategy → red-team for gaming). In brief:
- Identify or select a domain adapter (
adapters/*.md). If none fits, draft an inline adapter followingreferences/domain-adapter-contract.md. - Propose candidate metrics (the adapter's menu is a prior, not the answer — reason from the goal). Score each on measurability, latency, noise, alignment, gameability, and cost. Prefer alignment over convenience for the primary.
- Pick ONE primary objective, a set of guardrail metrics that must not regress, a trial budget (wall-clock and/or cost per trial), and a stop condition (budget exhausted, plateau over K trials, or target hit).
- Choose the accept/reject strategy for this domain:
deterministic-delta(fast, low-noise),significance-test, orbandit(noisy/delayed/expensive — e.g. ads). - Name the Goodhart guards (guardrail metrics, holdout, periodic critic).
- Write
runs/<id>/CHARTER.md. Confirm it with the user before spending real budget if trials cost money or touch production.
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- adapters/bug-finding.md 3.4 KB
- adapters/code-generation.md 2.8 KB
- adapters/code-perf-audit.md 5.8 KB
- adapters/google-ads.md 3.2 KB
- adapters/web-onboarding.md 5.1 KB
- DESIGN.md 11 KB
- examples/code-perf-demo/.auto/checks.sh 110 B runs code
- examples/code-perf-demo/.auto/ideas.md 275 B
- examples/code-perf-demo/.auto/log.jsonl 1011 B
- examples/code-perf-demo/.auto/measure.sh 162 B runs code
- examples/code-perf-demo/.auto/prompt.md 634 B
- examples/code-perf-demo/bench.js 783 B runs code
- examples/code-perf-demo/gen.js 849 B runs code
- examples/code-perf-demo/RESULTS.md 682 B
- examples/code-perf-demo/solution.js 967 B runs code
- examples/code-perf-demo/test.js 1.2 KB runs code
- README.md 3.4 KB
- references/domain-adapter-contract.md 2.2 KB
- references/journal-schema.md 1.4 KB
- references/metric-discovery.md 4.2 KB
- references/runtime-contract.md 3.7 KB
- scripts/arl.mjs 14 KB runs code
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.
- 1mo ago First seen · 61 lines · 120 tokens per session scan A 721e9fd122f6
autoresearch-loop is a skill published in the GitHub repository jdrhyne/agent-skills (240 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,857 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other skills, from other repositories
pillow
Manipulate images locally using Python and PIL/Pillow. Use when the user asks to resize, crop, rotate, flip, filter, enhance, combine, overlay, watermark, add text to, convert, compress, create, or edit images locally. Also use for thumbnails, borders, color adjustments, transparency, animated GIFs, or extracting…
skill-creator
Create or update OpenBotX skills. Use when users want to create a new skill, modify an existing one, or need guidance on skill structure, frontmatter, bundled resources, or best practices. Also use when the user says "turn this into a skill" or wants to capture a workflow as a reusable skill.
http-client
Make HTTP requests (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) to APIs and web services. Use when the user needs to call a REST API, fetch data from an endpoint, send form data, upload files, download files, or test HTTP services.
browser
Automate browser interactions for web scraping, testing, and navigation. Use when the user needs to visit a webpage, interact with UI elements, take screenshots, or extract content from rendered pages.
Post tweets on Twitter/X. Use when the user wants to tweet, post on X, create threads, or share content on Twitter. Requires the "twitter" auth profile configured in httpclient.
cron
Schedule reminders, recurring tasks, and one-time events. Use when the user asks to be reminded of something, schedule a periodic check, set an alarm, or automate a task at a specific time or interval.