oguzdogmus/mimir / skills/mimir-core-rules
mimir-core-rules
VerifiedHard rules for Mimir, the exam study plugin. Load this before any other Mimir skill runs and before reading, writing, or acting on a course workspace (the learning root, default ~/learning/, or any Mimir .state/ file).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.8 KB |
| references/recording.md | markdown | 1.8 KB |
| references/session-close.md | markdown | 1.8 KB |
| references/verified-items.md | markdown | 4.0 KB |
references/session-close.md
View on GitHub# Shared session close
Used by study, quiz and past-question sessions, only when the student asks to end the session (Ending a session in core rules), including after zero items. Use file read/write/edit tools for memory changes.
A skill that rewrites save.md before this close keeps its last_session, pending_debrief and `delivery_choice:` lines as the file has them now: step 2 sets the first two, and only `session.py start` writes `delivery_choice:`.
1. Run `session.py now` with `{}`, then `session.py close` with `{"now": "<its now>", "term": "<term>", "course": "<course>", "log": "<log name>", "started": "<S>"}`. It appends `ended: <now>` to this session's `started: <S>` block once and reports the session length (`minutes`); when the block already has its `ended:` stamp it writes nothing and returns that stamp (`already_closed` true). Never write an `ended:` line yourself. Use its `last_session` for save.md.
2. Read save.md. Edit only last_session and pending_debrief, preserving its other fields and template. Set pending_debrief to <start.exam_date> <start.exam_name, else exam> only when it is empty or no and start.exam is set; preserve an existing pending exam. A repeated close after both writes is a no-op.
3. Read the current log. Preserve every existing first_contact line. If start.first_contact was null and this session log has none, add first_contact: <S> once. Append any gate disagreements not already logged under ## Verifier disagreements, verbatim.
If interrupted between the log and save edits, run this close again: `session.py close` returns the stored stamp and its `last_session`, so the missing save edit uses the existing end time, never a new one. Completion means one ended stamp for this start, the matching last_session, and a preserved or newly set pending_debrief.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |