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.
npx agentmods add rules/baijum/ukulele-companion/session-learninggit clone --depth 1 https://github.com/baijum/ukulele-companionWhat 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.
| Model | Per session | Once 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 |
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.
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
-
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?
-
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
-
Draft rule updates:
- Check if an existing
.cursor/rules/*.mdcfile covers the pattern - If yes: update the existing rule with new examples
- If no: create a new rule following
cursor_rules.mdcformat
- Check if an existing
-
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
globstargeting
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.
- yesterday First seen · 46 lines · 0 tokens per session scan A 431fb55c8388
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.
Other cursor rules, from other repositories
cursorrules
You are an expert in SceneView, the #1 open-source 3D & AR SDK for Android and iOS.
project-conventions
PriceGrab project conventions (override selected global rules).
project-status
PriceGrab shipped state and product backlog (read first).
specify-rules
For additional context about the active feature, technologies, project structure, shell commands, and other important information.
tune-tangler-project
Tune Tangler — conventions, repo layout, doc links.
git-consent
Git — consent for commits/push; amend; context before risky git ops.