Lesson Memory Recorder

What it does

When your agent uses it

• Recording a rule after the user corrects your approach
• Saving a hard-won lesson so it is not relearned next time
• Recalling past lessons before starting similar work

Example prompts

• “Learn this: always run migrations before seeding test data.”
• “Save a lesson from that correction about the CI test command.”
• “Recall any lessons about deploying this service before I start.”

Requirements

• A connected agent memory store with lesson save and recall tools

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Distill the user's text into one imperative rule: what to do or avoid, plus the consequence that makes it matter. Strip the incident…
2. 2Set context to the trigger situation, the moment a future session should apply it.
3. 3Set confidence: 0.7 for a direct user correction, 0.5 for a self-observed pattern.
4. 4Scope with project when the rule is repo-specific; omit it for universal rules.
5. 5If this is a repeat correction, save the same content verbatim; the duplicate strengthens the existing lesson instead of forking a variant.
6. 6Confirm with the rule as saved, so the user can veto a bad distillation.

What it can do on your machine

Read from SKILL.md and the folder at commit 007a1a7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lesson Memory Recorder loads about 721 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 340 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~721

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rohitg00/agentmemory at commit 007a1a7, republished under its Apache-2.0 licence (© rohitg00). 340 words, ~721 tokens.

name

lesson

description

Save a correction or hard-won rule as a confidence-weighted lesson that resurfaces before similar work. Use when the user corrects your approach, says "learn this", "always" or "never do X", or you notice yourself repeating a past mistake.

argument-hint

[the rule learned]

user-invocable

true

memory_lesson_save {
  "content": "Run vitest with --run in CI contexts; bare vitest enters watch mode and hangs the pipeline.",
  "context": "any script or CI step that invokes vitest",
  "confidence": 0.7,
  "project": "myrepo"
}

Lesson saved (confidence 0.7). Duplicate content will strengthen it.

© rohitg00, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugin/skills/lesson of rohitg00/agentmemory.

Open the folder on GitHubat commit 007a1a7