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.
git clone --depth 1 https://github.com/queelius/claude-anvilWrote 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.
[](https://agentmods.dev/plugins/queelius/claude-anvil/pub-pipeline)<a href="https://agentmods.dev/plugins/queelius/claude-anvil/pub-pipeline"><img src="https://agentmods.dev/badge/plugins/queelius/claude-anvil/pub-pipeline/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.
<a href="https://agentmods.dev/plugins/queelius/claude-anvil/pub-pipeline"><img src="https://agentmods.dev/badge/plugins/queelius/claude-anvil/pub-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pub-pipeline 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.
What it actually says
{
"name": "pub-pipeline",
"version": "0.9.0",
"description": "Unified publication pipeline: R packages (CRAN/JOSS/JSS) and Python packages (PyPI)",
"author": {
"name": "Alexander Towell",
"email": "[email protected]",
"url": "https://metafunctor.com"
},
"repository": "https://github.com/queelius/claude-anvil",
"license": "MIT",
"keywords": [
"R",
"CRAN",
"JOSS",
"PyPI",
"publication",
"academic",
"audit"
]
}
What it installs
The manifest is a name and a version. 6 skills, 5 commands, 5 agents travel with it, and installing the plugin installs all of them — 845 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill joss-draft A 56 tokens
- Skill joss-audit A 46 tokens
- Skill r-pub-pipeline A 46 tokens
- Skill cran-audit A 49 tokens
- Skill pub-pipeline A 40 tokens
- Skill pypi-publish B 53 tokens
- Command joss-audit A 10 tokens
- Command cran-audit A 9 tokens
- Command joss-draft A 13 tokens
- Command r-publish A 9 tokens
- Command pypi-publish A 7 tokens
- Agent joss-reviewer A 176 tokens
- Agent joss-writer A 198 tokens
- Agent field-scout A 42 tokens
- Agent community-auditor A 46 tokens
- Agent software-auditor A 45 tokens
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 · 22 lines scan A 1a868e0a5c66
pub-pipeline is a plugin published in the GitHub repository queelius/claude-anvil (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
julia-development
Modern Julia development with Julia 1.10+, package management, scientific computing, high-performance numerical code, and production best practices.
numerical
Numerical computing verification and optimization agent for Python/Dart ndarray, tensor, and scientific computing codebases.
nvidia-cuopt-skills
Agent skills for NVIDIA cuOpt: routing (VRP, TSP, PDP), LP/MILP/QP, installation (Python/C/developer), and REST server. Use when building or solving optimization with cuOpt.
functional-programming
Functional programming with Elixir, OTP patterns, Phoenix framework, and distributed systems.
powergridmodel
power-grid-model Python skill - high-performance steady-state distribution power system analysis: power flow, state estimation, and IEC 60909 short-circuit calculations with 22 component types and batch/parallel computation.
python-dev
Python development workflow with architecture design, coding guidelines, testing patterns, and specialized review agents.