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/JuanMarchetto/agent-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/juanmarchetto/agent-skills/learn-by-mistake)<a href="https://agentmods.dev/plugins/juanmarchetto/agent-skills/learn-by-mistake"><img src="https://agentmods.dev/badge/plugins/juanmarchetto/agent-skills/learn-by-mistake/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/juanmarchetto/agent-skills/learn-by-mistake"><img src="https://agentmods.dev/badge/plugins/juanmarchetto/agent-skills/learn-by-mistake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
learn-by-mistake 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.
What it actually says
{
"name": "learn-by-mistake",
"description": "Persistent error memory — analyzes failures, extracts root-cause lessons, and prevents the same mistake twice",
"version": "1.0.0",
"author": { "name": "Juan Marchetto" },
"homepage": "https://github.com/JuanMarchetto/learn-by-mistake-skill",
"repository": "https://github.com/JuanMarchetto/learn-by-mistake-skill",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 skill, 4 commands, 3 hooks travel with it, and installing the plugin installs all of them — 169 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.
- 1mo ago First seen · 10 lines scan A cb7db09b58ad
learn-by-mistake is a plugin published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo 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 2026-09-03.
Other plugins, from other repositories
devharness
Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.
mochi
A browser companion for AI assistants. Bundled MCP tools for Chrome automation, persistent project memory (Continuum chain), and an in-page hint modal — pair with the Mochi Chrome extension.
logs-locally-plugin
Store and browse AI agent session logs locally with a SQLite database and web UI.
governed-context
Governed memory (explicit states, fail-closed sensitivity gates, quarantine-only writes) as a dependency-free MCP server, plus a blind-evaluation protocol skill for honest A/B comparisons.
pwa-debug
Browser-side debug layer that exposes live PWA state (DOM, framework state, stores, events, library popups) to AI agents via MCP — eliminating the human copy/paste loop when debugging web apps with AI.
ccc-tools
Claude Code integration for cocoindex-code (ccc). Slash commands for onboarding, reset, and re-index; git hook installer for automatic incremental indexing; standard exclude presets that avoid common retrieval noise (tests, plans, compiled views, ML embedding data).