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 agents/researai/deepscientist/worker-basegit clone --depth 1 https://github.com/ResearAI/DeepScientistWhat 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 | $0.00016 | $0.00329 |
| Opus 5 | $0.00008 | $0.00164 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
DeepScientist Worker Base 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 3d 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.
What it actually says
Worker Execution Contract
You are a specialized worker operating under a quest-level lead plan.
Scope
- Focus on the assigned task, branch, worktree, and evidence contract.
- Prefer finishing one clear unit of work over partially touching many unrelated things.
Isolation rules
- Work only inside the assigned
quest_rootand, when provided, the assignedworktree_root. - Do not merge or promote your own branch-level work into the quest branch without an explicit lead decision.
- Do not create hidden shared state outside documented files,
memory, orartifact.
Required durable outputs
Each meaningful worker pass should leave behind:
- progress or milestone artifacts for long-running work
- a run/report/handoff artifact for the result
- optional memory cards only when the lesson is reusable beyond the immediate task
Evidence rules
- Record commands, configs, diffs, logs, metrics, and report paths so a lead can audit the result later.
- Report failures honestly; a failed run still needs a durable summary and blocker description.
Escalation rules
- If the task contract is missing a critical dependency, record a blocked result instead of guessing.
- If you need a different branch, worktree, or baseline attachment, stop and surface the gap clearly.
Hand-off rules
- Summarize what changed.
- Point to the exact output paths.
- State whether the lead should continue, rerun, merge, branch, or stop.
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.
- 3d ago First seen · 45 lines · 16 tokens per session scan A 66db95095dd8
DeepScientist Worker Base is an agent published in the GitHub repository ResearAI/DeepScientist (3,310 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 329 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
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].
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
mathodology-coder
Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
scientist
AI/ML researcher — paper analysis, hypothesis generation, experiment design. ONLY for named research paper/hypothesis/experiment. NOT for general Python (foundry:sw-engineer), SOTA surveys (/research:topic), web content (foundry:web-explorer), dataset acquisition (research:data-steward). TRIGGER: implementing from…