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
- 6
- requests
- 4
- upvotes
- 533
- planned
- 5,569
- shipped
- Planning bug: guard #4 says an advisory's reference is "a `blocked_by` to WIRE" — followed literally on a CROSS-STORY reference it produces a cross-parent edge, which gate 7 forbids
- Planning bug: `_shared.md` says "Epic is not an offered kind" — the MCP has offered it all along, so every pass routes around a tool that works
- A story whose deliverable was a PAGE planned no instrument that OPENS it until its last card — a client-boundary 500 lived through five green subtask PRs
- Planning bug: MOTIR-2853 read `ready: true` with two unexecutable preconditions — an external credential and a post-deployment soak window, neither expressible as an edge
- Planning bug: MOTIR-3249 gates four children behind a POST-DEPLOY measurement, so the story cannot be run as a parent
- Planning bug: two MOTIR-3249 children were pinned to ONE repo while their criteria need the other
- Planning bug: MOTIR-3229 names THREE homes and assigns home 2 to MOTIR-3203, which closed without it — `run.md`'s parent-run still stops only on a `design`/`manual` stopper
- Planning bug: an acceptance criterion named TWO triggers for one event-driven seam, and one of them is a non-terminating loop — the card's own explanation names only the other
- Planning bug: a grep-shaped acceptance criterion whose PATTERN also appears in the comments FORBIDDING it is unfalsifiable — MOTIR-3226's AC 7 returned 3 hits on `origin/main` at authoring time
- Planning bug: a card's own detection query prescribed `gh pr view --json files`, which caps at 100 — and the cap became a finding in the card's evidence table
- Planning bug: a contrast ratio was measured in ONE theme context and generalised to "light" — `data-palette` makes it twenty, and four of them failed
- Planning bug: `run.md` never says the at-scale lane is LABEL-gated, so a run labels the PR AFTER creating it — a second trigger at the same sha whose cancelled run poisons the card's CI verdict
- Planning bug: a design card specified a CONSTRUCTION (a true normal-offset band) without checking it was geometrically possible at the mark's own proportions
- Planning bug: the two-homes obligation is stated only in `CORPUS-MAINTENANCE.md`, which no planning pass loads — six occurrences, five sibling cards, no gate
- Planning bug MIRROR: (motir-ai) carry the widened deferral surfaces + the placeholder triggers into `SHARED_PLANNING_RULES`
- Planning bug: (motir-meta) a deferral written in a DESIGN ASSET or a source COMMENT is invisible to the deferral-is-a-card rule — the AI orb shipped a mock "M" for 18 days with no card
- Planning bug: a card's "Read and deliberately LEFT" section states a COMPLETENESS claim ("every other literal was read") that a re-run falsifies — a false absence the next card inherits
- Planning bug: the totality rule (#29) cannot reach a renderer keyed on a DATABASE-defined set — a `Record<Union, …>` is total against a union that is itself the hand-authored subset, so the compiler certifies the lie
- Planning bug: a card's SCOPE-PROXY criterion contradicted its own instruction criterion — "no `app/` path" forbade the very file another criterion required a comment in
- (motir-ai) Mirror the sweep-is-not-its-grep-pattern limb into `SHARED_PLANNING_RULES` — a pattern's silence is a result, never a scope verdict