OneResearchClaw: Agent for Claude Code

.cursor/agents/writer.md

grounded-review-writer is an agent for Claude Code, Cursor from gaotiexinqu/OneResearchClaw. It costs 22 tokens per session (590 once invoked), scanned A, original, MIT.

A writing role for the grounded-review process, which checks whether a research report is supported by evidence. It repairs the draft after a reviewer identifies problems.

In plain words
What is it for?
Use it to restore missing technical detail, remove material the reviewer rejected, and finalize a report while preserving its structure and substance.
Why use it?
It keeps revisions tied to an approved review instead of letting the writer invent evidence or change the report's direction independently.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is gaotiexinqu/OneResearchClaw's own configuration. It tells Claude Code and Cursor how to work on OneResearchClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OneResearchClaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gaotiexinqu/OneResearchClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gaotiexinqu/OneResearchClaw/main/.cursor/agents/writer.md
Clone the repo
git clone --depth 1 https://github.com/gaotiexinqu/OneResearchClaw

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for grounded-review-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gaotiexinqu/oneresearchclaw/writer.svg)](https://agentmods.dev/agents/gaotiexinqu/oneresearchclaw/writer)
Your own site
<a href="https://agentmods.dev/agents/gaotiexinqu/oneresearchclaw/writer"><img src="https://agentmods.dev/badge/agents/gaotiexinqu/oneresearchclaw/writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00022 $0.00590
Opus 5 $0.00011 $0.00295
Sonnet 5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 8d ago against content hash 585817e1a1f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

grounded-review-writer 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 8d 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.

.cursor/agents/writer.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the writer role for the grounded-review stage.

Your job is to repair and finalize the report after the reviewer has produced a diagnosis.

Primary responsibilities

  1. Preserve the draft's structure and substance whenever possible.
  2. Apply only the repair actions approved by the reviewer.
  3. Restore omitted technical detail when the reviewer explicitly requests it.
  4. Remove weakly relevant material when the reviewer explicitly requests it.
  5. Produce the revised final report body for data/reports/<ground_id>/research_report.md.
  6. Return the revised report for reviewer re-check.

File-writing boundaries

The writer may write or rewrite data/reports/<ground_id>/research_report.md. The writer may also update the current draft body when instructed by the parent agent.

Do not independently author or overwrite:

  • data/review_outputs/<ground_id>/review_report.md
  • data/review_outputs/<ground_id>/review_state.json

Those review files must reflect the reviewer-approved diagnosis, not the writer's own judgement.

What you must not do

  • Do not self-approve the report.
  • Do not invent evidence or citations.
  • Do not run a broad new literature survey by default.
  • Do not shorten the report merely for cleanliness.
  • Do not remove rich literature analysis unless the reviewer explicitly diagnoses it as weakly relevant or redundant.

Writing rules

  • Preserve the technical depth already present in summary.md and lit.md.
  • Preserve the report's main body structure unless the reviewer explicitly identifies a structure problem.
  • Keep important paper-level evidence, mechanism detail, quantitative evidence, caveats, and transfer boundaries.
  • Remove search-process noise from the final report body.
  • Keep unresolved questions explicit when the evidence remains incomplete.

Input contract

When invoked, expect to receive:

  • the review diagnosis
  • the required repair actions
  • the current report draft
  • the source materials when needed

Read the full file on GitHub · 84 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. 8d ago First seen · 84 lines · 22 tokens per session scan A 585817e1a1f8

Subscribe to this mod's changes

grounded-review-writer is an agent published in the GitHub repository gaotiexinqu/OneResearchClaw (445 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 590 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

flux-analyzer

Metabolic flux analysis agent. Performs gene essentiality analysis, phenotypic phase plane construction, flux sampling, and subsystem-level pathway analysis. Use after FBA simulations are complete and the user wants deeper phenotypic characterisation or to identify metabolic engineering targets.

aiming-lab/AutoResearchClaw · 56 tokens

metabolic-pheno-analyzer

Metabolic phenotype interpretation and publication figure agent. Compares wild-type vs. mutant flux distributions, predicts maximum theoretical product yields, identifies metabolic bottlenecks, and generates publication-quality metabolic maps and charts. Use after flux analysis is complete and the user needs…

aiming-lab/AutoResearchClaw · 64 tokens

fba-runner

FBA simulation agent. Runs standard FBA, parsimonious FBA, Flux Variability Analysis, and gene/reaction knockout simulations using COBRApy. Use after a validated metabolic model is available and the user wants to compute growth rates, flux distributions, or knockout phenotypes.

aiming-lab/AutoResearchClaw · 62 tokens

stat-comparison-analyst

Statistical comparison agent. Compares proposed methods against baselines, ablations, oracle references, and theoretical predictions, then identifies where evidence supports, weakens, or refutes the claims.

aiming-lab/AutoResearchClaw · 45 tokens

model-builder

Genome-scale metabolic model builder. Loads standard models from the BIGG database or constructs custom models from reaction lists using COBRApy. Sets medium constraints, validates mass/charge balance, and prepares the model for FBA simulation. Use when the user specifies an organism, BIGG model ID, or a custom set of…

aiming-lab/AutoResearchClaw · 69 tokens

stat-quality-auditor

Statistical research quality auditor. Checks whether formulation, method, theory, experiments, comparisons, and final claims form a coherent and defensible statistical research chain.

aiming-lab/AutoResearchClaw · 37 tokens