learn-session

Run one learning session under the learn-harness doctrine.

npx skills

npx skills add joshuaoliphant/claude-plugins --skill learn-session

Works for Codex, Cursor and other harnesses. Use -a <agent> to target one, e.g. -a codex.

Claude Code

/plugin marketplace add joshuaoliphant/claude-plugins
/plugin install learn-harness@oliphant-plugins

Learn session

Goal

Move the learner's understanding, availability or judgment on one goal, and leave the records updated so the next session starts where this one ended.

Hard rules

  • One question per turn, then end the turn. The answer decides the next question.
  • Never build on a step the learner hasn't demonstrated. A miss means repair first.
  • Commit before you ask. Every graded question, problem and Field rubric has its answer written to the session log before the learner sees the question.
  • Never put a graded question on a card or picker that marks a recommended option.
  • Close out every session, including abandoned ones.

Workflow

  1. Find the learn root. /mnt/project-files/learn/ in a Claude project, else learn/ in the working directory. No learn root: offer learn-harness:learn-setup and stop.
  2. Read the doctrine. Prefer the project's HARNESS.md (it may carry local edits); fall back to references/doctrine.md. Read all of it.
  3. Read the records: profile, frontier, session-feedback and curriculum (memory or files, per the doctrine's Records paragraph), plus the graph/ files relevant to the goal.
  4. Pick the session type from the request: Lesson, Practice or Field (doctrine section 1). Ambiguous: start a Lesson and say so.
  5. Open the session log from assets/session-log-template.md at sessions/<YYYY-MM-DD>-<slug>.md. Keep it current every turn.
  6. Run the session per the doctrine: Lesson section 3, Practice section 4, Field section 5, with section 2 governing every question and section 6 the voice.
  7. Close out per doctrine section 7: log, graph, ledger, frontier. Re-read each shared file right before writing it. Attach or link the session log in the closing message.

Answer format to ask for

answer / confidence % / thinking. Thinking is the primary data, often dictated: read it leniently for transcription noise and fully for the model it reveals.

← learn-harness