h-spec-cover

# h-spec-cover — Spec coverage analysis You are running coverage analysis via `mcp__haft__haft_query(action="coverage")`. Identifies modules with no decisions (blind) and modules with stale decisions (degraded). Output drives the operator's triage — frame a problem for blind modules, refresh for stale ones. ## Step 1 — Call coverage analysis ``` mcp__haft__haft_query( action="coverage", context="<optional context filter>" ) ``` Returns per-module status: - **governed** — module has at least one active decision - **stale** — module has decisions but they're past valid_until / R_eff degraded - **blind** — module has no decisions Within each tier modules are **sorted by impact-score descending** (per dec-20260527-e4b86938 V1): impact = number of governed modules that depend on this one. A blind module with high impact is high-priority (governed code at risk if it changes); a blind module with zero impact is an isolated utility, low priority. The `(impact: N)` tag in the output line surfaces the count when > 0; absence of tag = zero impact. ## Step 2 — Identify the immediate gap If the operator is currently editing a specific file, prioritize that file's module. Run: ``` mcp__haft__haft_query( action="related", file="<path operator is editing>" ) ``` Returns decisions whose `affected_files` include that path. If empty → the file is in a blind module (or governed only at parent module level — check governance_mode). ## Step 3 — Triage and recommend For each sign...