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/geekatron/jerryWrote 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/geekatron/jerry/jerry)<a href="https://agentmods.dev/plugins/geekatron/jerry/jerry"><img src="https://agentmods.dev/badge/plugins/geekatron/jerry/jerry/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/geekatron/jerry/jerry"><img src="https://agentmods.dev/badge/plugins/geekatron/jerry/jerry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
jerry 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
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. 32 skills, 2 commands, 89 agents, 6 hooks travel with it, and installing the plugin installs all of them — 10,054 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ux-ai-first-design A 206 tokens
- Skill ux-atomic-design A 152 tokens
- Skill ux-behavior-design A 193 tokens
- Skill ux-design-sprint A 189 tokens
- Skill ux-inclusive-design A 188 tokens
- Skill user-experience A 145 tokens
- Skill ux-heart-metrics A 144 tokens
- Skill ux-kano-model A 201 tokens
- Skill ux-lean-ux A 149 tokens
- Skill red-team A 92 tokens
- Skill ux-heuristic-eval A 128 tokens
- Skill ux-jtbd A 149 tokens
- Skill contract-design A 112 tokens
- Skill eng-team A 89 tokens
- Skill nasa-se A 65 tokens
- Skill orchestration A 43 tokens
- Skill pm-pmm A 167 tokens
- Skill pm-pmm A 167 tokens
- Skill saucer-boy-framework-voice A 84 tokens
- Skill use-case A 103 tokens
- Skill adversary A 51 tokens
- Skill problem-solving A 47 tokens
- Skill saucer-boy A 73 tokens
- Skill test-spec A 114 tokens
- Skill architecture A 29 tokens
- Skill prompt-engineering A 64 tokens
- Skill diataxis A 131 tokens
- Skill worktracker-decomposition A 35 tokens
- Skill ast A 33 tokens
- Skill bootstrap A 50 tokens
- Skill worktracker A 37 tokens
- Skill transcript D 61 tokens
- Command architect A 0 tokens
- Command release A 0 tokens
- Agent ux-ai-design-guide A 226 tokens
- Agent ux-sprint-facilitator A 224 tokens
- Agent ts-extractor A 23 tokens
- Agent ux-behavior-diagnostician A 183 tokens
- Agent ux-inclusive-evaluator A 199 tokens
- Agent ux-kano-analyst A 188 tokens
- Agent cd-generator A 108 tokens
- Agent nse-architecture A 38 tokens
- Agent nse-requirements A 45 tokens
- Agent nse-reviewer A 41 tokens
- Agent ps-critic A 43 tokens
- Agent ux-atomic-architect A 139 tokens
- Agent ux-heart-analyst A 130 tokens
- Agent ux-jtbd-analyst A 105 tokens
- Agent ux-lean-ux-facilitator A 140 tokens
- Agent ux-orchestrator A 121 tokens
- Agent wt-auditor A 22 tokens
- Agent wt-verifier A 11 tokens
- Agent cd-validator A 95 tokens
- Agent nse-configuration A 30 tokens
- Agent nse-explorer A 36 tokens
- Agent nse-integration A 29 tokens
- Agent nse-qa A 45 tokens
- Agent nse-reporter A 10 tokens
- Agent nse-risk A 38 tokens
- Agent nse-verification A 37 tokens
- Agent ps-analyst A 35 tokens
- Agent ps-architect A 25 tokens
- Agent ps-investigator A 31 tokens
- Agent ps-researcher A 36 tokens
- Agent ps-reviewer A 31 tokens
- Agent ps-synthesizer A 31 tokens
- Agent ts-parser A 22 tokens
- Agent tspec-analyst A 94 tokens
- Agent uc-author A 76 tokens
- Agent uc-slicer A 103 tokens
- Agent ux-heuristic-evaluator A 125 tokens
- Agent adv-executor A 33 tokens
- Agent adv-scorer A 52 tokens
- Agent orch-planner A 22 tokens
- Agent orch-synthesizer A 25 tokens
- Agent orch-tracker A 21 tokens
- Agent ps-reporter A 26 tokens
- Agent ps-validator A 20 tokens
- Agent sb-calibrator A 47 tokens
- Agent ts-formatter A 27 tokens
- Agent tspec-generator A 101 tokens
- Agent wt-visualizer A 24 tokens
- Agent eng-incident A 109 tokens
- Agent pe-builder A 71 tokens
- Agent pe-constraint-gen A 68 tokens
- Agent pe-scorer A 57 tokens
- Agent red-exploit A 81 tokens
- Agent red-infra A 98 tokens
- Agent sb-reviewer A 36 tokens
- Agent sb-rewriter A 42 tokens
- Agent ts-mindmap-ascii A 23 tokens
- Agent ts-mindmap-mermaid A 18 tokens
- Agent adv-selector A 41 tokens
- Agent diataxis-auditor A 51 tokens
- Agent eng-backend A 98 tokens
- Agent eng-devsecops A 117 tokens
- Agent eng-infra A 99 tokens
- Agent eng-security A 97 tokens
- Agent red-exfil A 92 tokens
- Agent red-lateral A 87 tokens
- Agent red-lead A 88 tokens
- Agent red-persist A 87 tokens
- Agent red-recon A 86 tokens
- Agent red-reporter A 85 tokens
- Agent red-social A 84 tokens
- Agent red-vuln A 79 tokens
- Agent sb-voice A 55 tokens
- Agent diataxis-classifier A 54 tokens
- Agent diataxis-explanation A 54 tokens
- Agent diataxis-howto A 65 tokens
- Agent diataxis-reference A 50 tokens
- Agent diataxis-tutorial A 70 tokens
- Agent eng-architect A 112 tokens
- Agent eng-frontend A 97 tokens
- Agent eng-lead A 99 tokens
- Agent eng-qa A 99 tokens
- Agent eng-reviewer A 109 tokens
- Agent pm-competitive-analyst B 101 tokens
- Agent pm-business-analyst B 107 tokens
- Agent pm-product-strategist B 104 tokens
- Agent pm-customer-insight B 100 tokens
- Agent pm-market-strategist B 107 tokens
- Agent red-privesc B 73 tokens
- Hook PreToolUse A not measured
- Hook SubagentStop A not measured
- Hook PreCompact A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook UserPromptSubmit A not measured
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.
- 1mo ago First seen · 117 lines scan A bd7c5d9a201a
jerry is a plugin published in the GitHub repository geekatron/jerry (37 stars, last pushed 5d 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 2026-08-30.
Other plugins, from other repositories
mempalace
Give your AI a memory — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, and guided setup.
basic-memory
The bridge between Claude's working memory and Basic Memory's durable knowledge graph — session briefings, pre-compaction checkpoints, and capture reflexes.
reviewable-html-workbench
Generate reviewable HTML documents, serve previews, collect comments, and feed review outcomes back into agent workflows.
typemux-cc
Python type-checker LSP multiplexer for Claude Code (pyright, ty, pyrefly).
lians
Bitemporal memory for Claude Code with deterministic supersession, point-in-time recall, local MCP, erasure proofs, and tamper-evident history.
cc-hud
Compact statusline HUD for Claude Code — context, agents, rate limits.