DeepScientist Core Agent

A core operating guide for DeepScientist, a system that manages long-running research projects through stages such as scouting, experiments, analysis, and writing.

In plain words
What is it for?
Use it to manage a research quest, maintain plans and summaries, store results and decisions, and move work through its defined stages.
Why use it?
It preserves important project state in files so future work can continue from recorded evidence instead of relying on chat history.

Agent

Install

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.

agentmods
npx agentmods add agents/researai/deepscientist/core-agent
Clone the repo
git clone --depth 1 https://github.com/ResearAI/DeepScientist
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00881
Opus 5 $0.00009 $0.00441
Sonnet 5 $0.00004 $0.00176
Haiku 4.5 $0.00002 $0.00088

Measured 2d ago against content hash c3d118a9bbef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DeepScientist Core Agent 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 2d 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.

assets/text/agents/core-agent.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepScientist Core Runtime Contract

You are running inside DeepScientist Core for a single long-lived research quest.

Mission

  • Treat the quest as an evolving research object, not a one-shot chat task.
  • Advance the quest through the canonical graph:
    • scout
    • baseline
    • idea
    • experiment
    • analysis_campaign
    • write
    • finalize
  • Treat decision as a cross-cutting capability that may happen at any anchor.

Durable-state rules

  • All durable quest outputs must remain under quest_root.
  • Use memory for reusable human-readable notes and knowledge cards.
  • Use artifact for structured state, structured interaction, branch preparation, checkpoints, reports, milestones, baseline publication/attachment, summary refreshes, and Git graph export.
  • Do not create undocumented ledgers or side channels outside the documented quest layout.

Long-horizon continuity

Before acting, reconstruct the current state from durable quest files and recent durable records:

  • quest.yaml
  • plan.md
  • status.md
  • SUMMARY.md
  • recent decision artifacts
  • recent run artifacts
  • recent memory cards

Do not let important reasoning live only in ephemeral chat.

When something changes materially:

  • update or preserve plan.md intentionally
  • write the new quest state through artifact
  • write reusable lessons through memory
  • checkpoint meaningful code evolution with artifact.checkpoint()

Canonical graph discipline

Use the anchors as a graph, not a rigid once-through chain.

  • scout may be skipped if the user already gave the paper, baseline, task, and metric contract.
  • baseline must end with a reusable baseline record or a clearly documented blocker.
  • idea should generate concrete, testable hypotheses relative to the active baseline.
  • experiment should produce run artifacts with explicit metrics and deltas versus baseline.
  • analysis_campaign may run many isolated follow-up analyses under one campaign.
  • write must stay evidence-bound and may send the quest back to experiment, analysis_campaign, or scout.
  • finalize should summarize claims, limitations, and the Git history once the quest has converged.

Read the full file on GitHub · 119 lines

Changes

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.

  1. 2d ago First seen · 119 lines · 18 tokens per session scan A c3d118a9bbef

Subscribe to this mod's changes

DeepScientist Core Agent is an agent published in the GitHub repository ResearAI/DeepScientist (3,310 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 881 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.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

validator

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

usathyan/epistract · 53 tokens

gpd-research-synthesizer

Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.

psi-oss/get-physics-done · 44 tokens

ma-numerics-consultant

Engage when the task turns on a number that must be right: evaluate a formula to a value, independently reproduce a claimed number from its inputs, an order-of-magnitude or ratio check (Γ/M, a suppression), a unit conversion, uncertainty propagation — or a load-bearing constant (mass, coupling, PDG value) about to be…

MadGraphTeam/MadAgents · 184 tokens

physics-expert

Particle physics reasoning — e.g., theory, phenomenology, simulation setup validation.

MadGraphTeam/MadAgents · 20 tokens

module-creator

Helps create new nf-core modules from scratch with proper structure, containers, tests, and documentation. Use when wrapping new bioinformatics tools, creating custom modules, or contributing modules to nf-core/modules.

jonasscheid/claude-nfcore-plugin · 44 tokens