DeepScientist is a local research studio that manages the cycle from baseline experiments through research findings and paper-ready outputs. Researchers use it to organize autonomous scientific investigations, review progress, and take control when needed. The catalogue add-ons provide workflows and agent integrations for running research projects with it.
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 agentmods add skills/researai/deepscientist/baselinenpx skills add ResearAI/DeepScientist --skill baselinegit clone --depth 1 https://github.com/ResearAI/DeepScientistWrote 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/researai/deepscientist/baseline)<a href="https://agentmods.dev/skills/researai/deepscientist/baseline"><img src="https://agentmods.dev/badge/skills/researai/deepscientist/baseline.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 | $0.00028 | $0.03712 |
| Opus 5 | $0.00014 | $0.01856 |
| Sonnet 5 | $0.00006 | $0.00742 |
| Haiku 4.5 | $0.00003 | $0.00371 |
Grade A, and why
baseline 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 6d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline
Use this skill to secure one trustworthy comparator and then get out of the way. The target is one accepted baseline line, not an endless reproduction diary.
Match signals
Use baseline when:
- no credible baseline exists yet
- the current baseline is unverified or stale
- the user already has a baseline package that should be attached or imported
- a local code path or local service should be verified as the comparator
- a reproduction failed earlier and now needs repair
- the quest resumed and the baseline trust state is unclear
Do not use baseline when:
- a verified active baseline already exists and the next move is obviously
idea,experiment,write, orfinalize - the baseline gate was already explicitly waived for the current route
One-sentence summary
Secure the lightest trustworthy comparator, make the comparison contract explicit, then confirm, waive, or block the baseline and stop.
Control workflow
- Choose the current acceptance target and the lightest route that can satisfy it.
Prefer
attach,import, orverify-local-existingbefore full reproduction. - Make the comparator identity and core metric contract explicit. Record task, dataset, split, evaluation path, required metric ids, metric directions, source identity, and known deviations.
- Collect only the evidence needed to establish comparability. Do not widen into broad codebase audit or heavy reruns unless the lighter route cannot be trusted.
- Verify before acceptance. Check that outputs are real, metrics trace to real evidence, and the intended dataset/split and metric definitions match the contract. Explicitly verify the comparator and metric contract before treating the baseline gate as open.
- Close the gate explicitly.
Call
artifact.confirm_baseline(...), callartifact.waive_baseline(...), or record an explicit blocker and next route. When an already accepted baseline needs a deliberate second-pass refresh after verified code, variant, or canonical metric changes, preferartifact.overwrite_baseline(...)over pretending the update is just a first confirmation.
What ships with it
9 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.
- references/artifact-flow-examples.md 3.2 KB
- references/artifact-payload-examples.md 900 B
- references/baseline-checklist-template.md 1.5 KB
- references/baseline-plan-template.md 1.2 KB
- references/boundary-cases.md 2.5 KB
- references/codebase-audit-checklist.md 973 B
- references/comparability-contract.md 692 B
- references/operational-guidance.md 3.7 KB
- references/route-selection.md 727 B
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.
- 6d ago First seen · 327 lines · 28 tokens per session scan A 086559ce02e7
baseline is a skill published in the GitHub repository ResearAI/DeepScientist (3,314 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 3,712 once invoked, about $0.0001 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.
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…