mod: Ext 3 — human-readable proof explanation (mod/explain), 164/164

mod/explain renders a decision's proof tree into legible text: action + rule,
evidence line, and each derivation goal with [proved]/[unproved] and the
unification bindings that satisfied it (e.g. {B=ann, N=3, S=dave}). Pure SX over
the Phase-2 proof data — the audit trail's 'why' made readable. +10 tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

plans/mod-on-sx.md

@@ -16,7 +16,7 @@ federation extension.
 
 ## Status (rolling)
 
-`bash lib/mod/conformance.sh` → **154/154** (roadmap done + extensions in progress)
+`bash lib/mod/conformance.sh` → **164/164** (roadmap done + extensions in progress)
 
 ## Ground rules
 
@@ -142,11 +142,20 @@ lib/mod/fed.sx
   `(:score-at-least N)` → `aggregate_all(sum(W), signal(Id, _, W), T), T >= N`.
   Many weak signals accumulate past a threshold — genuine Prolog arithmetic
   aggregation. Default policy untouched.
-- [ ] Ext 3 — human-readable proof explanation (render a decision's `:goals`)
+- [x] **Ext 3 — proof explanation** (`lib/mod/explain.sx`, +10). `mod/explain`
+  renders a decision into a readable "why": action + rule, evidence line, and the
+  derivation goal-by-goal with `[proved]`/`[unproved]` marks and unification
+  bindings. E.g. `Report rc: escalate (rule: repeated-escalate)` … `[proved]
+  report(rc, B, S), report_count(S, N), N >= 3  {B=ann, N=3, S=dave}`.
 - [ ] Ext 4 — report linking / dedup (relations between reports about one subject)
 
 ## Progress log
 
+- **Ext 3 — proof explanation, 164/164** (+10). `mod/explain` turns the Phase-2
+  proof tree into human-readable text — the audit trail's "why" made legible. Pure
+  SX over existing decision data; no engine change. Renders unification bindings
+  inline (`{B=ann, N=3, S=dave}`) so a moderator sees exactly which facts proved
+  the decision.
 - **Ext 2 — weighted/aggregate scoring, 154/154** (+8). `:signals` + the
   `(:score-at-least N)` condition push aggregation into Prolog
   (`aggregate_all(sum(W), …)`), so low-confidence signals can accumulate to a