writing_agent

writing_agent is an agent for Claude Code from Xiangyue-Zhang/auto-deep-researcher-24x7. It costs 8 tokens per session (215 once invoked), scanned A, original, Apache-2.0.

An agent role for turning experiment logs and results into reports, summaries, research documents, and result tables.

In plain words
What is it for?
Use it to summarize experiments, compile result tables, explain findings, and document next steps in Markdown files.
Why use it?
It gives research writing a consistent output structure and separates reporting from the underlying experiment work.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to summarize experiments, compile result tables, explain findings, and document next steps in Markdown files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent
About the project

Auto Deep Researcher 24x7 is an autonomous AI agent that runs and monitors deep learning experiments continuously. Researchers use it to automate experiment execution, including hyperparameter tuning and GPU or Slurm-based workloads. The catalogue add-ons provide agents, skills, and instructions for operating the experiment workflow.

Xiangyue-Zhang/auto-deep-researcher-24x7 · 1,291 stars · on GitHub · arxiv.org

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.

Clone the repo
git clone --depth 1 https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7

Made for: Claude Code.

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 writing_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent/github.svg)](https://agentmods.dev/agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent)
Your own site
<a href="https://agentmods.dev/agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent"><img src="https://agentmods.dev/badge/agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent/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.

agentmods 80×15 button for writing_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent"><img src="https://agentmods.dev/badge/agents/xiangyue-zhang/auto-deep-researcher-24x7/writing_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 215 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 $0.00008 $0.00215
Opus 5 $0.00004 $0.00108
Sonnet 5 $0.00002 $0.00043
Haiku 4.5 $0.00001 $0.00021

Measured 12d ago against content hash 2bbffeb3f17d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

writing_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 12d 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.

agents/writing_agent.md · 44 lines

What it actually says

Writing Agent

You are the Writing agent. Your role is to generate reports, summaries, and research documentation.

Tools Available

  • write_file: Create reports and documents
  • read_file: Read experiment logs and results
  • list_files: Browse available files

Tasks You Handle

  1. Progress Reports: Summarize recent experiments, key findings, and next steps
  2. Result Tables: Compile experiment results into structured tables
  3. Analysis Documents: Write detailed analysis of experimental findings

Output Format

Always write to files (Markdown preferred). Structure reports as:

# Report Title
Date: YYYY-MM-DD

## Summary
Brief overview of findings.

## Results
| Experiment | Config | Metric | Notes |
|------------|--------|--------|-------|
| ...        | ...    | ...    | ...   |

## Analysis
Detailed interpretation.

## Next Steps
Recommended directions.
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. 12d ago First seen · 44 lines · 8 tokens per session scan A 2bbffeb3f17d

Subscribe to this mod's changes

writing_agent is an agent published in the GitHub repository Xiangyue-Zhang/auto-deep-researcher-24x7 (1,291 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 215 once invoked, about $0.0000 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.