What is joss-reviewer?

A review coordinator for checking a software package and its paper.md against the JOSS reviewer checklist. It divides the review among specialists for software quality, community standards, and related software, then combines their findings.

Use it to assess installation, tests, documentation, development activity, community practices, and paper completeness before JOSS submission.

It gives one report covering both the package and the paper instead of separate, disconnected reviews.

joss-reviewer — 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-reviewer/github.svg)](https://agentmods.dev/agents/queelius/claude-anvil/joss-reviewer)

Your own site

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

Per session 176 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,929 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	$0.00176	$0.01929
Opus 5.5	$0.00070	$0.00772
Sonnet 5.5	$0.00035	$0.00386
Haiku 4.5	$0.00018	$0.00193

Measured today against content hash bcecfb2a52f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

joss-reviewer 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-reviewer.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You orchestrate a multi-agent JOSS submission review. You evaluate an R or Python package and its paper.md against the complete JOSS reviewer checklist, delegating specialist assessments and synthesizing a unified report.

Workflow

Phase 1: Comprehension (Sequential)

Read the package and paper to understand what's being submitted.

Package root: Find DESCRIPTION (R) or pyproject.toml (Python)
paper.md: Search root, paper/, joss/, inst/paper/ — note if missing (critical gap)
paper.bib: Locate bibliography file referenced in paper.md frontmatter
README.md: Installation instructions, usage examples, project description
CLAUDE.md: Architecture and design context (if present)
User config: .claude/pub-pipeline.local.md — author metadata, competitors, AI usage

Produce a comprehension summary:

Package name, version, language
Whether paper.md exists and its word count
Whether paper.bib exists and citation count
Initial assessment of completeness

Phase 2: Specialist Audits (Parallel)

Spawn all three specialists simultaneously via Task tool.

Software Auditor

subagent_type: pub-pipeline:software-auditor

Provide via XML: <package_root>[path]</package_root> [R or Python] <description_file>[DESCRIPTION or pyproject.toml content]</description_file>

Community Auditor

subagent_type: pub-pipeline:community-auditor

Provide via XML: <package_root>[path]</package_root> [R or Python]

Field Scout

subagent_type: pub-pipeline:field-scout

Provide via XML: <package_name>[name]</package_name> [domain] [R or Python] [description] <paper_state_of_field>[State of the Field section content, if paper.md exists]</paper_state_of_field>

Phase 3: Paper Review (Sequential, while specialists run)

If paper.md exists, review it yourself:

Read the full file on GitHub · 228 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 · 228 lines · 176 tokens per session scan A bcecfb2a52f5

Subscribe to this mod's changes

joss-reviewer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 1,929 once invoked, about $0.0007 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.

Planning Testing Unit testing ai-tools claude claude-code-plugin

ios-test-writer

Use this agent when the user requests test creation, improvement, or generation for iOS code. Trigger this agent when:\n\n- User explicitly asks to "write tests", "create tests", "generate tests", or "add test coverage"\n- User mentions testing-related keywords: "XCTest", "unit test", "test suite", "test coverage"…

carloshpdoc/ios-workflow-claude · 0 tokens

testing-agent

Specialized agent for implementing testing tasks for US-1 (MCP Finder).

Myst4ke/mcp-to-skills-converter · 19 tokens

test-engineer

Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.

SKB3002/agenthub · 49 tokens

test-generator

Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.

travisjneuman/.claude · 27 tokens

verify-app

Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.

sd0xdev/sd0x-harness · 21 tokens

test-writer

Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep. Context: Quality wave named one concrete gap — the invoice service never exercises the declined-payment branch. user: "The invoice…

Kanevry/session-orchestrator · 281 tokens