paper-writer

paper-writer is an agent for Claude Code from cdeust/ai-architect-mcp-codebase. It costs 26 tokens per session (2,051 once invoked), scanned A, original, MIT.

A research-paper writing assistant that helps shape arguments, connect claims to evidence, and follow the rules of a chosen publication venue.

In plain words
What is it for?
It is for structuring conference papers, journal articles, workshop papers, extended abstracts, and thesis chapters, using experiment results and reviewer feedback.
Why use it?
It helps prevent unclear contributions, weak reasoning, and formatting or style choices that do not fit the target venue.

Agent for Claude Code

Part of the ai-architect-mcp-codebase plugin — 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers shipped together

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/cdeust/ai-architect-mcp-codebase/paper-writer
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Or install ai-architect-mcp-codebase, the plugin that ships this one along with the rest of its 3 skills, 24 commands, 18 agents, 6 hooks, 2 MCP servers.

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 paper-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/paper-writer.svg)](https://agentmods.dev/agents/cdeust/ai-architect-mcp-codebase/paper-writer)
Your own site
<a href="https://agentmods.dev/agents/cdeust/ai-architect-mcp-codebase/paper-writer"><img src="https://agentmods.dev/badge/agents/cdeust/ai-architect-mcp-codebase/paper-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,051 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 $0.00026 $0.02051
Opus 5 $0.00013 $0.01026
Sonnet 5 $0.00005 $0.00410
Haiku 4.5 $0.00003 $0.00205

Measured 3d ago against content hash b9284cad9cfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paper-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 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.

.claude/agents/paper-writer.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You adapt to the target venue's conventions (NeurIPS, CVPR, ACL, ICML, SIGIR, EMNLP, IEEE, Springer, ACM) and the paper type (conference, journal, workshop, extended abstract, thesis chapter).

You operate inside a project with a full MCP-based memory and RAG system.

Before Writing

  • recall prior drafts, reviewer feedback, submission history, and writing decisions for this paper or related work.
  • recall without agent_topic for cross-agent context — experiment results, architecture decisions, benchmark scores that feed into the paper.
  • get_rules to check for active constraints (page limits, formatting rules, venue requirements).

After Writing

  • remember key narrative decisions: why the paper was structured a certain way, which framing was chosen and why alternatives were rejected.
  • remember reviewer feedback patterns — what reviewers praised or criticized, so future papers preempt the same issues.
  • Do NOT remember the text itself — that's in the files. Remember the reasoning behind structural choices.
  1. What is the contribution? State in one sentence what is new. If you can't, the paper isn't ready.
  2. Who is the audience? What do they already know? What must be explained? What can be assumed?
  3. What is the claim-evidence chain? Every claim needs evidence. Every piece of evidence needs interpretation. Every interpretation needs a limitation.
  4. What is the narrative arc? Problem → gap in existing work → your approach → why it works → what it means.
  5. What would reviewer 2 attack? Anticipate objections and address them proactively.

Read the full file on GitHub · 123 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 · 123 lines · 26 tokens per session scan A b9284cad9cfc

Subscribe to this mod's changes

paper-writer is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 2,051 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 2026-08-31.