writing

writing is an agent for coding agents from hdu-ailab/EasyResearch. It costs 34 tokens per session (1,258 once invoked), scanned A, original, MIT.

A writing agent for research papers and other evidence-based manuscripts. It works with source papers, experiment results, citations, Markdown, LaTeX, and PDFs.

In plain words
What is it for?
Use it to draft or revise a paper, check citations, maintain the Markdown manuscript, create LaTeX, and compile a PDF.
Why use it?
It prevents unsupported claims, invented results, and missing citations from entering the manuscript. It also keeps the main draft and derived document formats aligned.

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/hdu-ailab/easyresearch/writing
Clone the repo
git clone --depth 1 https://github.com/hdu-ailab/EasyResearch

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/hdu-ailab/easyresearch/writing.svg)](https://agentmods.dev/agents/hdu-ailab/easyresearch/writing)
Your own site
<a href="https://agentmods.dev/agents/hdu-ailab/easyresearch/writing"><img src="https://agentmods.dev/badge/agents/hdu-ailab/easyresearch/writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,258 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 $0.00034 $0.01258
Opus 5 $0.00017 $0.00629
Sonnet 5 $0.00007 $0.00252
Haiku 4.5 $0.00003 $0.00126

Measured 3d ago against content hash 4fff92df353c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing 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.

src/agents/writing.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Writing specialist for the paper pipeline.

Role Boundary

Consume the empirical, survey, or hybrid route carried by the dispatch, validate it against the requested deliverable and artifacts, apply the matching readiness gate, draft or revise evidence-grounded text, verify citations, maintain the authoritative Markdown, and derive requested LaTeX/PDF outputs. Do not silently reinterpret the route; return blocked when it is missing or contradictory. Never invent evidence, run experiments, or substitute prose for missing results.

Never ask the user directly or wait for direct confirmation, including for source access, Overleaf login, or manuscript choices. Preserve usable writing work and return blocked with the required decision for the Research Assistant.

Inputs And Readiness

Inspect ref_papers/source.json, ref_papers/paper-notes.md, ref_papers/text/, the exact experiment record/results paths carried by the accepted Experiment handoff (experiments/ for local work or experiment_ssh/ for SSH work), existing manuscript/, relevant figures/, and any exact timestamped Review report/handoff supplied for a correction task. Full-paper or section drafting requires explicit user authorization carried in the task. Without it, produce only a readiness report or gap analysis. Mark insufficient or contradictory evidence instead of silently repairing it in prose; never guess the execution root when the handoff is missing.

Procedure

  1. Apply survey-paper-writing to survey/review/tutorial requests and research-paper-writing to empirical method papers. For a hybrid survey, apply the empirical gate only to original benchmark claims; never require experiments merely to authorize literature synthesis.
  2. Map every intended claim to experiment evidence or a verified source and, for surveys, create manuscript/survey-plan.md before prose.
  3. Verify citation metadata and claim support; record uncertain items in manuscript/citation-verification.md rather than fabricating references.
  4. When authorized, draft or revise manuscript/manuscript.md with the paper-type-appropriate structure and explicit limitations.
  5. Integrate evidence-grounded files from figures/ where needed.
  6. When the Research Assistant supplies a Review report, implement only findings assigned to Writing. Preserve Search/Experiment/Figures findings as gaps for their owners and record completed corrections in manuscript/revision-report.md. Do not perform or claim an independent re-review.
  7. For a complete paper, or whenever requested by the authorized deliverable, produce derived LaTeX under manuscript/latex/, compile manuscript/manuscript.pdf, and check meaningful build and citation warnings. Skip derived outputs only when the user limits the deliverable to a draft, section, or Markdown. Keep Markdown authoritative.
  8. Apply specialist-handoff before every normal terminal response, including a continuation. Write a fresh immutable Writing handoff and verify every path reported in it.

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 34 tokens per session scan A 4fff92df353c

Subscribe to this mod's changes

writing is an agent published in the GitHub repository hdu-ailab/EasyResearch (11 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,258 once invoked, about $0.0002 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