moooon
Motir
Vibe the project. Bring an idea — Motir's three AI layers plan it, track it, and ship it, end to end. You're looking at Motir, built in Motir.
- Vibe Project
- Open Source
- AI Agent
- AI Loop
- 5
- suggestions
- 4
- votes
- 489
- planifiés
- 4 378
- livrés
- Planning bug: a comment listing what an API does NOT publish was read as the publication — a whole decision question was built on it
- PLANNING BUG — one prompt asked a QUESTION and gave an INSTRUCTION about the same page; only the question got a decision gate, so the instruction reached three commits before anyone asked whether the product wanted it
- PLANNING BUG — a container whose child's job is to FILE CARDS can never finish its own PR, and its title promised what the merge cannot deliver
- Planning bug: the third denominator swap, and `COMPRESSION.measure.py`'s `TAG_LINES = 1` contradicts § Decision 1's two-line tag — so § Decision 4's 1 600-line target is unreachable too
- Planning bug: a card asserted two Playwright lanes were interchangeable by RENAME, having compared their globs and never their webServer env
- Planning bug: a cross-parent dependency was recorded in PROSE because the planner believed a different parent means no `blocked_by` edge is available (MOTIR-2768 → MOTIR-2764)
- Planning bug: a card headed "One PR" carried an acceptance criterion naming a file in the OTHER repo
- Planning bug: an AC that reads as a totality claim on two axes — every item, every project, exactly once — left the LIFECYCLE axis unbounded, and the surface's own copy was already asserting it
- Planning bug: a correct mechanism produced a wrong outcome and I concluded the INPUT was illegitimate — three cards filed to prohibit a shape the product needed to support
- Planning bug: a document said "a separate surface with no card in this story" and no card was filed anywhere — while a downstream criterion read "the full suite passes"
- Planning bug: an acceptance criterion quoted an inventory's COUNT, on the card guaranteed to run after 400+ files of its own predecessors' work landed
- Planning bug: MOTIR-2796 was partitioned from a scanner that reads only lib/repositories, so a whole second population had no card — and the guard that would have found it was scheduled LAST
- Planning bug: MOTIR-2797 declared a sibling's 423-file substrate "landed" when it sits on an unmerged branch with no PR — and MOTIR-2734's placement makes the two stories deadlock
- Planning bug: the story pinned a write path to motir-core without verifying motir-core can produce a vector — it holds no embedding credential at all
- Planning bug: MOTIR-2659's AC 5 set a line target from a corpus-wide warrant share, and the region's own measurement puts the floor at 204
- Planning bug: an acceptance criterion was written in a metric the card's own scope forbids it from moving — and the metric was mis-attributed at source
- Planning bug: a new surface's SCOPE was settled from competitor precedent without reading the shell tier it was being placed in — and the card had to invent a duplicate nav row to make the mismatch fit
- Planning bug: a card's method clause was written in the semantics of an UNMERGED branch, and its criterion named a card archived 13 minutes after authoring
- Planning bug: read a card's own `pg_policies` fact as reassurance when it named the table breaking four of its eight reads
- PLANNING BUG — the hosting migration swept its own Story's cards and no others; 20 not-done cards in four other Stories still plan against Vercel