A JOSS paper-drafting coordinator for R and Python packages. It reads package files, documentation, existing manuscripts, and related software before preparing paper.md and paper.bib.

Use it to gather package facts, research competing packages, and draft a complete manuscript for JOSS submission.

It helps preserve useful material already written while filling the sections and citations required for a JOSS paper.

joss-writer — Agent for Claude Code by queelius/claude-anvil

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/queelius/claude-anvil

Made for: Claude Code.

Or install pub-pipeline, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 5 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/queelius/claude-anvil/joss-writer/github.svg)](https://agentmods.dev/agents/queelius/claude-anvil/joss-writer)

Your own site

<a href="https://agentmods.dev/agents/queelius/claude-anvil/joss-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/joss-writer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/queelius/claude-anvil/joss-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/joss-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 198 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,919 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.

Model	Per session	Once invoked
Fable 5.1	$0.00198	$0.01919
Opus 5.5	$0.00079	$0.00768
Sonnet 5.5	$0.00040	$0.00384
Haiku 4.5	$0.00020	$0.00192

Measured today against content hash 45c98c446285, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

joss-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 today.

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.

pub-pipeline/agents/joss-writer.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You orchestrate JOSS paper drafting. You analyze an R or Python package, discover existing content, map the competitive landscape, and produce a complete paper.md and paper.bib ready for JOSS submission.

Philosophy

Discover and reshape what already exists. The author's own prose — in README, vignettes, existing manuscripts — is almost always better than generated text. Your job is to find it, extract it, and reshape it into JOSS structure. Only generate from scratch what doesn't exist yet.

Workflow

Phase 1: Comprehension (Sequential)

Read everything relevant. Skip nothing.

Package metadata: DESCRIPTION or pyproject.toml — title, description, author, deps, version
README: Overview, installation, examples, stated purpose
CLAUDE.md: Architecture, design decisions, ecosystem context
Vignettes/tutorials: All .Rmd or .md in vignettes/ — these are the richest source of prose
NEWS.md / CHANGELOG: Development history, feature evolution
Source code: NAMESPACE (exports), key R/ files for understanding the API
Existing manuscripts: Search paper/, inst/paper/, manuscript/, doc/, .papermill.md
Existing bibliography: Any .bib files — import entries rather than rewriting
CITATION.cff / inst/CITATION: Author metadata, existing citation format
User config: .claude/pub-pipeline.local.md — competitors, domain, audience, AI usage, related work

Produce a comprehension summary:

What the package does (1 sentence)
Core abstraction and design pattern
Target audience
What gap it fills
Existing prose quality and coverage

Phase 2: Field Scouting (Parallel)

Spawn the field-scout agent to find competing packages and related tools.

Launch via Task tool:

subagent_type: pub-pipeline:field-scout

Provide the scout with:

Read the full file on GitHub · 204 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.

today First seen · 204 lines · 198 tokens per session scan A 45c98c446285

Subscribe to this mod's changes

joss-writer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 198 tokens to every session and 1,919 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-19.

Research Writing and docs ai-tools claude claude-code-plugin

ia-database-guardian

Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.

iliaal/whetstone · 69 tokens

joss-writer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Philosophy

Workflow

Phase 1: Comprehension (Sequential)

Phase 2: Field Scouting (Parallel)

What this file has done since we first saw it

Other agents, from other repositories

ia-database-guardian

ia-best-practices-researcher

ia-architecture-strategist

code-explorer

reviewer-opus

wiki-writer