lessons-learned
Automatic mistake capture and proactive lesson injection for AI coding agents. Mines conversation logs for mistake patterns, structures them as indexed lessons, and injects relevant warnings before the agent repeats the mistake.
By Joe BlackLicense: MIT0 GitHub starsUpdated 5 days ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 2 skill or MCP entries
- Source updated
- Sep 18, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install lessons-learned for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install lessons-learned@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/joeblackwaslike/lessons-learnedClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .claude-plugin/plugin.json├── skills/lessons-learned/SKILL.md└── .mcp.json
Included Skills1
Use for the lessons-learned plugin — adding a lesson, capturing a coding mistake, scanning session logs for candidates, promoting/archiving candidates, browsing active lessons, tuning injection settings, auditing the lesson store (dead triggers, unreachable lessons, truncated summaries, near-duplicates), retracting a lesson tag, scoping a lesson to the current project, batch-importing lessons from JSON, or running the lesson effectiveness eval suite. Use when the user types /lessons:add, /lessons:review, /lessons:manage, /lessons:config, /lessons:doctor, /lessons:cancel, /lessons:scope, /lessons:help, /lessons:onboard, or /lessons:eval, or asks what lessons are active, how to get started, how injection works, what commands exist, or what changed recently. Do not wait for the user to name this plugin explicitly — if they ask about capturing mistakes, lesson candidates, the scan-promote pipeline, or lesson injection into context, this skill applies.
MCP servers1
- command
- npx
- args
- promptfoo mcp
Plugin manifests1
{
"name": "lessons-learned",
"description": "Automatic mistake capture and proactive lesson injection for AI coding agents. Mines conversation logs for mistake patterns, structures them as indexed lessons, and injects relevant warnings before the agent repeats the mistake.",
"author": {
"name": "Joe Black"
},
"homepage": "https://github.com/joeblackwaslike/lessons-learned",
"repository": "https://github.com/joeblackwaslike/lessons-learned.git",
"license": "MIT",
"keywords": [
"lessons",
"mistakes",
"patterns",
"injection",
"hooks",
"dedup",
"scanner"
],
"commands": [
"commands/add.md",
"commands/backup.md",
"commands/cancel.md",
"commands/config.md",
"commands/doctor.md",
"commands/eval.md",
"commands/help.md",
"commands/manage.md",
"commands/onboard.md",
"commands/review.md",
"commands/scope.md"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[lessons-learned on Agent Plugins Marketplace](https://pluginsmp.com/plugins/lessons-learned)