a2698a80cfe528496beef794f9b207635253cd5f
Skills Issue #1 (compound-hallucination hardening) shipped a new optional profile slot, `spec_validation.parsers`, that maps markdown fence labels to validation commands. Three new gates consume it: brainstorm Step 7 parse-every-block, planner Step 5 parse-the-bytes-you-inline, and the grounding-check code-block parse pass. A profile written before the slot existed has all three running as silent no-ops — exactly the failure mode the raw-buf.2 spec slipped through. Register three fence labels: - `ail` → `ail check {file}` — Form-A surface modules. `check` is strictly broader than `parse` (catches the parser-novel head class AND the type-level rejects an MVP-only construct triggers, e.g. polymorphic fn-type without explicit forall), so it would have BLOCKED the storage-tag / RawBuf-shorthand / implicit-forall chain at Step 7 of brainstorm. - `ail-json` → `ail check {file}` — JSON AST form; `check` auto-detects extension. - `ll` → `llvm-as {file} -o /dev/null` — LLVM IR snippets in codegen specs. Verified `ail check` works on a standalone Form-A file (no workspace setup needed; the loader injects prelude + kernel).
iter raw-buf.1-intercept-registry (DONE 5/5): try_emit_primitive_instance_body → registry table (refs #7)
plan: raw-buf.2-kernel-manifest — 7-task crate-rename + RawBuf submodule + checker-side surface (refs #7)
iter prep.3-kernel-tier-modules (DONE 9/9): kernel-tier modules + param-in + stub crate — closes #33
iter prep.3-kernel-tier-modules (DONE 9/9): kernel-tier modules + param-in + stub crate — closes #33
Description
No description provided
Languages
Rust
91.6%
Python
4.6%
C
1.8%
LLVM
1.6%
Shell
0.4%