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/optimiziramsi/skillsWrote 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/optimiziramsi/skills/lessons)<a href="https://agentmods.dev/plugins/optimiziramsi/skills/lessons"><img src="https://agentmods.dev/badge/plugins/optimiziramsi/skills/lessons/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/optimiziramsi/skills/lessons"><img src="https://agentmods.dev/badge/plugins/optimiziramsi/skills/lessons.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
lessons 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 2d 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.
What it actually says
{
"name": "lessons",
"displayName": "optimiziramsi lessons",
"version": "0.1.0",
"description": "Learn once, keep it — retro harvests a session's learnings, lessons curates them in .agent/lessons/, and the lesson-scout agent finds prior art before you re-debug.",
"author": {
"name": "optimiziramsi",
"url": "https://github.com/optimiziramsi"
},
"homepage": "https://github.com/optimiziramsi/skills/tree/main/lessons#readme",
"repository": "https://github.com/optimiziramsi/skills",
"license": "MIT",
"keywords": [
"lessons",
"retro",
"knowledge"
]
}
What it installs
The manifest is a name and a version. 2 skills, 2 commands, 1 agent travel with it, and installing the plugin installs all of them — 327 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 2d ago First seen · 19 lines scan A d239d7d09f50
lessons is a plugin published in the GitHub repository optimiziramsi/skills (2 stars, last pushed 3d ago), 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
code-refactoring
Code cleanup, refactoring automation, and technical debt management with context restoration.
misakanet
Failure-memory network for AI coding agents: search evidence-rated failure lessons before re-debugging, and turn new failures into shared knowledge.
leankg
Lightweight knowledge graph for AI-assisted development. Impact analysis, code search, dependency tracking, and context generation.
dynatrace
Connect Claude Code to your Dynatrace environment and investigate production issues, review deployments, and check for vulnerabilities using real data pulled directly into your session: root cause details, logs, metrics, traces, and CPU/memory profiling. Ask in plain language and get answers grounded in what's…
ix-memory
Ix Memory integration — transforms Claude into a graph-reasoning agent with cognitive skills for understanding, investigation, impact analysis, planning, debugging, architecture auditing, and deep documentation synthesis.
simba
Unified Claude Code plugin: error memory, semantic recall, CLAUDE.md guardian.