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/ammawla/encode-toolkitWrote 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/ammawla/encode-toolkit/plugin)<a href="https://agentmods.dev/plugins/ammawla/encode-toolkit/plugin"><img src="https://agentmods.dev/badge/plugins/ammawla/encode-toolkit/plugin/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/ammawla/encode-toolkit/plugin"><img src="https://agentmods.dev/badge/plugins/ammawla/encode-toolkit/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
encode-toolkit 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 1mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What it installs
The manifest is a name and a version. 47 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 4,665 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cross-reference A 88 tokens
- Skill scientific-writing A 117 tokens
- Skill track-experiments A 41 tokens
- Skill cite-encode A 46 tokens
- Skill compare-biosamples A 88 tokens
- Skill epigenome-profiling A 106 tokens
- Skill functional-screen-analysis A 55 tokens
- Skill integrative-analysis A 125 tokens
- Skill multi-omics-integration A 174 tokens
- Skill pipeline-atacseq A 117 tokens
- Skill pipeline-chipseq A 114 tokens
- Skill pipeline-guide A 147 tokens
- Skill pipeline-rnaseq A 99 tokens
- Skill quality-assessment A 102 tokens
- Skill regulatory-elements A 137 tokens
- Skill scrna-meta-analysis A 156 tokens
- Skill single-cell-encode A 130 tokens
- Skill variant-annotation A 146 tokens
- Skill batch-analysis A 90 tokens
- Skill cellxgene-context A 86 tokens
- Skill clinvar-annotation A 77 tokens
- Skill data-provenance A 0 tokens
- Skill disease-research A 133 tokens
- Skill download-encode A 43 tokens
- Skill gwas-catalog A 86 tokens
- Skill hic-aggregation A 80 tokens
- Skill jaspar-motifs A 90 tokens
- Skill liftover-coordinates A 61 tokens
- Skill methylation-aggregation A 107 tokens
- Skill motif-analysis A 104 tokens
- Skill peak-annotation A 92 tokens
- Skill pipeline-cutandrun A 93 tokens
- Skill pipeline-dnaseseq A 91 tokens
- Skill pipeline-hic A 84 tokens
- Skill pipeline-wgbs A 103 tokens
- Skill search-encode A 43 tokens
- Skill visualization-workflow A 104 tokens
- Skill ensembl-annotation A 152 tokens
- Skill gnomad-variants A 146 tokens
- Skill gtex-expression A 75 tokens
- Skill histone-aggregation A 82 tokens
- Skill publication-trust A 145 tokens
- Skill ucsc-browser A 136 tokens
- Skill accessibility-aggregation A 85 tokens
- Skill geo-connector A 121 tokens
- Skill bioinformatics-installer B 140 tokens
- Skill setup C 28 tokens
- MCP server encode-toolkit A not measured
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.
- 1mo ago Changed a3d37fd0be44
- 1mo ago Changed 59d1f1cc2d16
- 1mo ago First seen · 22 lines scan A aab365b8a759
encode-toolkit is a plugin published in the GitHub repository ammawla/encode-toolkit (21 stars, last pushed 26d ago), licensed AGPL-3.0. 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 2026-08-30.
Other plugins, from other repositories
proteus
Proteus skills for public-safe structural biology automation and molecular visualization workflows.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.