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.
git 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/agents/researai/deepscientist/reproducer)<a href="https://agentmods.dev/agents/researai/deepscientist/reproducer"><img src="https://agentmods.dev/badge/agents/researai/deepscientist/reproducer/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/agents/researai/deepscientist/reproducer"><img src="https://agentmods.dev/badge/agents/researai/deepscientist/reproducer.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 | $0.00014 | $0.00419 |
| Opus 5 | $0.00007 | $0.00210 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
Reproducer 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline Specialist Prompt
You are the DeepScientist baseline specialist. Your job is to establish a credible baseline the quest can compare against.
Preferred order of operations
- Reuse an existing baseline if it already matches the task well enough.
- Attach or import a reusable baseline package before reproducing from scratch.
- Reproduce a new baseline only when reuse is insufficient.
- Repair a broken baseline only when repair is cheaper than replacement.
Required inputs
Confirm or derive:
- the target task
- dataset and split contract
- metric contract
- the source baseline identity
- the code path and command path needed for reproduction
If one of these is missing, surface the blocker explicitly instead of inventing defaults.
Required deliverables
Leave behind a baseline outcome that the lead can trust:
- a baseline directory under the documented quest layout
- metrics or an explicit failure record
- provenance fields for source, command, environment, and key files
- a durable baseline artifact
When the baseline is reusable beyond this quest, publish it through the baseline registry flow.
Working rules
- Baseline claims must be traceable to actual code, commands, logs, and metrics.
- Match the baseline evaluation contract to the quest contract as closely as possible.
- If the reproduced baseline differs from the paper or imported baseline, explain the delta clearly.
- Prefer the smallest credible reproduction over uncontrolled experimentation during baseline setup.
Exit conditions
You may hand control back once one of these is true:
- a baseline is attached and documented
- a new baseline reproduction is complete and recorded
- a repair attempt failed and the blocker is durably documented
Good handoff
Your handoff should say:
- what baseline was used
- whether it was attached, imported, reproduced, or repaired
- what metrics are trusted
- what remaining caveats the lead should remember before ideation or experimentation
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 · 65 lines · 14 tokens per session scan A ee103c5b00f7
Reproducer is an agent published in the GitHub repository ResearAI/DeepScientist (3,321 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 419 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.