session-learning

A manual end-of-session review that turns repeated coding lessons into project rules. It updates or creates Markdown rule files used by Cursor.

In plain words
What is it for?
Use it after a major feature, fix, repeated feedback, or a newly established pattern to identify rule changes and commit them separately from feature code.
Why use it?
It helps prevent the same style, accessibility, API, or bug-prevention guidance from being rediscovered in later sessions.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/baijum/ukulele-companion/session-learning
Clone the repo
git clone --depth 1 https://github.com/baijum/ukulele-companion

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00359
Opus 5 $0.00000 $0.00179
Sonnet 5 $0.00000 $0.00072
Haiku 4.5 $0.00000 $0.00036

Measured yesterday against content hash 431fb55c8388, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-learning 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 yesterday.

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.

.cursor/rules/session-learning.mdc · 46 lines

What it actually says

Session Learning Workflow

At the end of a coding session, review corrections and patterns that emerged. This rule is triggered manually by the developer when they want to codify session learnings.

When to Run

  • After completing a significant feature or fix
  • When the same feedback was given multiple times in a session
  • When a new pattern was established that should be standardized

Process

  1. Review session corrections:

    • What formatting/style issues were caught by ktlint or detekt?
    • What accessibility patterns needed to be applied?
    • What API patterns were repeated?
  2. Identify rule candidates:

    • Pattern used in 3+ locations → consider a new rule
    • Bug that would be prevented by a rule → add to existing rule
    • New library/API usage → document conventions
  3. Draft rule updates:

    • Check if an existing .cursor/rules/*.mdc file covers the pattern
    • If yes: update the existing rule with new examples
    • If no: create a new rule following cursor_rules.mdc format
  4. Track in git:

    • Commit rule changes separately from feature code
    • Use commit type Docs: for rule-only changes

Rule Quality Checklist

  • Rule is actionable (tells the agent what to do, not just what exists)
  • Includes a concrete code example from the actual codebase
  • References the canonical file location
  • Doesn't duplicate existing rules
  • Has correct globs targeting
Changes

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.

  1. yesterday First seen · 46 lines · 0 tokens per session scan A 431fb55c8388

Subscribe to this mod's changes

session-learning is a cursor rule published in the GitHub repository baijum/ukulele-companion (13 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 359 tokens. 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.