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/jgsystemsconsulting/jgs-se-knowledge-packsWrote 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/jgsystemsconsulting/jgs-se-knowledge-packs/jgs-se-knowledge-packs)<a href="https://agentmods.dev/plugins/jgsystemsconsulting/jgs-se-knowledge-packs/jgs-se-knowledge-packs"><img src="https://agentmods.dev/badge/plugins/jgsystemsconsulting/jgs-se-knowledge-packs/jgs-se-knowledge-packs/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/jgsystemsconsulting/jgs-se-knowledge-packs/jgs-se-knowledge-packs"><img src="https://agentmods.dev/badge/plugins/jgsystemsconsulting/jgs-se-knowledge-packs/jgs-se-knowledge-packs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
jgs-se-knowledge-packs 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 10d 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 65 skills travel with it, and installing the plugin installs all of them — 12,061 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill nasa-fault-management A 269 tokens
- Skill nasa-se-expanded A 278 tokens
- Skill sebok A 298 tokens
- Skill dau-se-guidebook A 179 tokens
- Skill dod-mq-bok A 269 tokens
- Skill dod-rio A 302 tokens
- Skill dod-te-guidebook A 281 tokens
- Skill faa-ams-vv A 243 tokens
- Skill faa-hf-std A 327 tokens
- Skill faa-req-handbook A 233 tokens
- Skill faa-rma A 279 tokens
- Skill faa-system-safety A 348 tokens
- Skill gao-agile A 228 tokens
- Skill gao-cost A 272 tokens
- Skill gao-schedule A 192 tokens
- Skill mil-hdbk-61 A 294 tokens
- Skill nasa-ceh A 237 tokens
- Skill nasa-de-acquisition A 261 tokens
- Skill nasa-npr-7150 A 197 tokens
- Skill nasa-pra A 235 tokens
- Skill nasa-rm-standard A 255 tokens
- Skill nasa-systems-modeling A 255 tokens
- Skill nist-800-37 A 223 tokens
- Skill nist-cps A 233 tokens
- Skill nist-stat-handbook A 268 tokens
- Skill sd-22-dmsms A 218 tokens
- Skill digital-systems-engineering A 193 tokens
- Skill dod-digital-engineering A 205 tokens
- Skill dod-mosa A 268 tokens
- Skill dodaf A 109 tokens
- Skill eu-ai-act A 103 tokens
- Skill gao-tra A 152 tokens
- Skill mil-std-882 A 66 tokens
- Skill nasa-npr-7123 A 125 tokens
- Skill nasa-schedule A 259 tokens
- Skill nist-csf A 98 tokens
- Skill nist-sse A 189 tokens
- Skill se-standards-signpost A 180 tokens
- Skill nasa-hsi A 121 tokens
- Skill nasa-risk A 99 tokens
- Skill nasa-se-handbook A 140 tokens
- Skill nasa-system-safety A 98 tokens
- Skill nist-800-171 A 113 tokens
- Skill nist-ai-rmf A 98 tokens
- Skill nist-ssdf A 109 tokens
- Skill dafman-63-119 A 124 tokens
- Skill dod-vva-rpg A 115 tokens
- Skill dote-te-guidebook A 127 tokens
- Skill mil-hdbk-338 A 156 tokens
- Skill nist-800-61 A 109 tokens
- Skill cisa-cpg A 93 tokens
- Skill doe-o-413-3 A 130 tokens
- Skill doe-sem A 102 tokens
- Skill faa-std-025 A 101 tokens
- Skill federal-bca A 110 tokens
- Skill is-gps-200n A 115 tokens
- Skill mil-hdbk-516 A 119 tokens
- Skill mil-std-40051 A 108 tokens
- Skill mil-std-881f A 109 tokens
- Skill nasa-ms-7009 A 136 tokens
- Skill nasa-std-8719-14 A 125 tokens
- Skill requirements-writing A 110 tokens
- Skill omg-signpost A 104 tokens
- Skill faa-sem C 321 tokens
- Skill mrl-deskbook C 248 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 12 lines scan A 2846abdbd36c
jgs-se-knowledge-packs is a plugin published in the GitHub repository jgsystemsconsulting/jgs-se-knowledge-packs (5 stars, last pushed 20d ago), with no licence file. 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 2026-08-31.
Other plugins, from other repositories
edulab
A collection of educational skills that turn school subject questions into interactive teaching webpages. It covers 3D geometry, analytic geometry, conic sections, and chemical reactions.
master-skill
A collection of Buddhist AI assistant skills based on Buddhist texts and commentaries, covering teachers and traditions from India, China, Tibet, and Theravāda Buddhism.
hypha
Hypha is the AI agent of the Mycelium ecosystem: a connecting filament between engineers and the SysML v2 specification. Provides skills and subagents for KerML/SysML v2 metamodel lookup, standard model library lookup, normative spec citation, and SysML v2 textual-notation validation.
manim-skills
Manim (math animation) skills for AI coding agents — animate equations, plot functions, and render 3Blue1Brown-style explainers to MP4 with Manim Community Edition.
understanding
Understand a topic or a bug: minimal explanations and root-cause diagnosis.
unslop
Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…