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.
git clone --depth 1 https://github.com/eliransu/digital-brainnpx agentmods add skills/eliransu/digital-brain/autoresearchWrote 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/eliransu/digital-brain/autoresearch)<a href="https://agentmods.dev/skills/eliransu/digital-brain/autoresearch"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/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/eliransu/digital-brain/autoresearch"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/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 | $0.00124 | $0.01810 |
| Opus 5 | $0.00062 | $0.00905 |
| Sonnet 5 | $0.00025 | $0.00362 |
| Haiku 4.5 | $0.00012 | $0.00181 |
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 9d 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 — 21 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoresearch: Autonomous Research Loop
You are a research agent. You take a topic, run iterative web searches, synthesize findings, and file everything into the wiki. The user gets wiki pages, not a chat response.
This is based on Karpathy's autoresearch pattern: a configurable program defines your objectives. You run the loop until depth is reached. Output goes into the knowledge base.
Before Starting
Read references/program.md to load the research objectives and constraints. This file is user-configurable. It defines what sources to prefer, how to score confidence, and any domain-specific constraints.
Topic Selection
Three paths to a topic:
A. Explicit topic (always respected)
When the user says /autoresearch [topic] or "research X", use the given topic verbatim and skip the sections below.
B. Boundary-first selection (agenda control, opt-in)
This is agenda control, not pure memory. DragonScale Memory.md Mechanism 4 labels this mechanism as such because it shapes which direction the research agent moves next. Users who want a strict memory-layer subset should omit this path entirely.
When /autoresearch is invoked WITHOUT a topic AND the vault has adopted DragonScale, default to surfacing the frontier of the vault as a set of candidate topics the user can accept, override, or decline.
Feature detection (shell):
if [ -x ./scripts/boundary-score.py ] && [ -d ./.vault-meta ] && command -v python3 >/dev/null 2>&1; then
BOUNDARY_MODE=1
else
BOUNDARY_MODE=0
fi
When BOUNDARY_MODE=1:
- Run
./scripts/boundary-score.py --json --top 5. Returns the top 5 frontier pages byboundary_score = (out_degree - in_degree) * recency_weight. - Helper failure handling: if the helper exits non-zero, emits invalid JSON, or returns an empty
resultsarray, setBOUNDARY_MODE=0and fall through to section C below. Do NOT prompt the user with an empty candidate list, and do NOT improvise a topic. - Present the candidate list to the user: "Your top frontier pages are: [list]. Research which one? (1-5, or type a topic to override, or say 'cancel' to be asked normally.)"
- If the user picks 1-5, use the selected page's title as the topic.
- If the user types free text, use that.
- If the user cancels or does not choose, fall through to C.
What ships with it
1 file 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.
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.
- 9d ago First seen · 229 lines · 124 tokens per session scan A 46191b1748d2
autoresearch is a skill published in the GitHub repository eliransu/digital-brain (1 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,810 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 21 lines, and is treated as a copy.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
review
Review branch changes against Archcore docs, or report project health. Use for 'review my branch', 'review the changes before merge', 'show status', 'documentation gaps', 'check if docs match code', 'close out the feature', 'ship the feature and close it out', or after a staleness warning. --drift for staleness…
migrate
Scan the project and migrate existing documentation into OKF format. Use when the user wants to populate the knowledge base from existing docs, README, schemas, API specs, runbooks, or any structured project knowledge. Trigger on "migrate to okf", "populate the knowledge base", "scan my docs", "convert docs to okf"…
digest
Generate a structured vibe-learn learning digest of the current coding session from .vibe-learn/session-log.jsonl.
fec-nuxt-project-standard
A guide for building Nuxt 3 applications with Vue 3 and TypeScript. Nuxt is a framework for Vue that can render pages on the server, generate static pages, or run as a browser-only app, using file-based routes and built-in data-fetching patterns.