Refine purpose-first communication framing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: DarKWinGTM

README.md

@@ -181,7 +181,7 @@ for f in $RULE_FILES; do cp "$f" ~/.claude/rules/; done
 
 | Rule | Purpose | Key Benefit |
 |:-----|:--------|:------------|
-| [`accurate-communication.md`](accurate-communication.md) | Clear, honest communication | No vague claims, no over-strong contradiction wording, reusable partial-evidence technical snapshot wording, stronger human-language glosses, clearer explanation of variables/fields/config keys/internal labels when answers depend on them, goal-qualified proposal wording for advisory future-work ideas, honest duplicate-looking team-agent reporting, governing-basis clarification before deep branch analysis, compact post-compact re-anchor wording, natural-professional wording, direct human-readable action/result wording preferred over metaphor-heavy internal shorthand, continuation-first guidance, clearer recommendation-plus-reason next-step wording that still preserves alternatives when multiple paths are real, and active summaries that keep resolved topics available for reasoning without repeating them as current issues by default |
+| [`accurate-communication.md`](accurate-communication.md) | Clear, honest communication | No vague claims, no over-strong contradiction wording, reusable partial-evidence technical snapshot wording, stronger human-language glosses, clearer explanation of variables/fields/config keys/internal labels when answers depend on them, goal-qualified proposal wording for advisory future-work ideas, honest duplicate-looking team-agent reporting, governing-basis clarification before deep branch analysis, compact post-compact re-anchor wording, natural-professional wording, direct human-readable action/result wording preferred over metaphor-heavy internal shorthand, main-point-first framing for diagnosis/test/recommendation/proposal/update answers, continuation-first guidance, clearer recommendation-plus-reason next-step wording that still preserves alternatives when multiple paths are real, and active summaries that keep resolved topics available for reasoning without repeating them as current issues by default |
 | [`artifact-initiation-control.md`](artifact-initiation-control.md) | Startup artifact governance | Resolve design/changelog/TODO/phase/patch posture before meaningful governed work drifts, while keeping patch non-default during greenfield startup unless a real before/after review surface exists |
 | [`authority-and-scope.md`](authority-and-scope.md) | Decision hierarchy | User authority respected, fresh user directives override previously offered assistant options, unnecessary option branching is discouraged when one safe continuation path already exists, future-work proposals stay advisory until explicitly selected, user-declared RULES-first issues stay RULES-first instead of being diverted into memory-first fixes, unresolved governing-basis selection stays user-owned unless authority/evidence already settles it, compacted-session continuation re-anchors to the latest active directive and active frame, and overlapping team expansion stays advisory unless a distinct new role is actually needed |
 | [`custom-agent-selection-priority.md`](custom-agent-selection-priority.md) | Custom agent selection priority | Prefer visible user custom agents as the primary specialist pool when a task clearly matches them, and reuse an existing matching teammate before spawning another overlapping team role |
@@ -199,7 +199,7 @@ for f in $RULE_FILES; do cp "$f" ~/.claude/rules/; done
 | [`runtime-topology-control.md`](runtime-topology-control.md) | Runtime topology discipline | Bounded inspect-first, one-authority-at-a-time runtime mutation posture that prevents debug-by-expansion and requires explicit approval for additive or authority-changing topology moves |
 | [`recovery-contract.md`](recovery-contract.md) | Blocked-response contract | Every constrained/refused path has actionable next steps |
 | [`tactical-strategic-programming.md`](tactical-strategic-programming.md) | Tactical vs strategic doctrine | Tactical entry stays fast, but every tactical move must point toward a declared strategic target and convergence path |
-| [`natural-professional-communication.md`](natural-professional-communication.md) | Communication style doctrine | Default to calm, human-readable, non-robotic, non-character-driven professional communication, and reject metaphor-heavy or management-style abstraction when direct wording would be clearer |
+| [`natural-professional-communication.md`](natural-professional-communication.md) | Communication style doctrine | Default to calm, human-readable, non-robotic, non-character-driven professional communication, reject metaphor-heavy or management-style abstraction when direct wording would be clearer, and front-load the operational purpose when the answer would otherwise bury it behind warm-up framing |
 | [`refusal-classification.md`](refusal-classification.md) | Deterministic refusal taxonomy | Consistent block decisions and traceable output modes |
 | [`refusal-minimization.md`](refusal-minimization.md) | False-refusal reduction | Prefer recoverable constrained/context paths when authorized |
 | [`strict-file-hygiene.md`](strict-file-hygiene.md) | File hygiene | Prevent junk files while allowing required governed startup artifacts |
@@ -216,8 +216,8 @@ for f in $RULE_FILES; do cp "$f" ~/.claude/rules/; done
 
 | Rule | Purpose | Key Benefit |
 |:-----|:--------|:------------|
-| [`answer-presentation.md`](answer-presentation.md) | Answer presentation standards | Readable and orderly responses with compact titled snapshots, small fact tables, stronger grouped scope-boundary sections, full-set-first / next-stage presentation, natural-flow formatting, compact governing-basis clarification blocks, compact post-compact re-anchor blocks for compacted-session continuation, compact variable-role structures for identifier-heavy explanations, compact near-term gloss support for abstract internal phrasing, and compact proposal layouts that distinguish advisory future-work ideas from queued execution |
-| [`explanation-quality.md`](explanation-quality.md) | Explanation structure quality | Plain-language-first, step-by-step reasoning with stronger what-it-is/what-it-is-not, now-versus-later, user-visible-outcome, short-recap, whole-set-first, stage-progression, good-operator explanation flow, stop-before-overexplaining boundaries, direct translation of architecture-first or metaphor-heavy wording into human-readable action/result language, a governing-basis clarification boundary before deep multi-branch explanation, a compact post-compact re-anchor boundary before explanation resumes after compaction, explicit support for unpacking variables/fields/config keys/internal labels before deeper reasoning, explicit deferral of continuation-vs-option policy to accurate-communication, and goal-qualified proposal framing when future ideas are offered after bounded completion |
+| [`answer-presentation.md`](answer-presentation.md) | Answer presentation standards | Readable and orderly responses with purpose-first framing near the start of diagnosis/test/recommendation/proposal/update answers, compact titled snapshots, small fact tables, stronger grouped scope-boundary sections, full-set-first / next-stage presentation, natural-flow formatting, compact governing-basis clarification blocks, compact post-compact re-anchor blocks for compacted-session continuation, compact variable-role structures for identifier-heavy explanations, compact near-term gloss support for abstract internal phrasing, and compact proposal layouts that distinguish advisory future-work ideas from queued execution |
+| [`explanation-quality.md`](explanation-quality.md) | Explanation structure quality | Plain-language-first, step-by-step reasoning with a purpose-first explanation step for diagnosis/test/recommendation/proposal/update answers, stronger what-it-is/what-it-is-not, now-versus-later, user-visible-outcome, short-recap, whole-set-first, stage-progression, good-operator explanation flow, stop-before-overexplaining boundaries, direct translation of architecture-first or metaphor-heavy wording into human-readable action/result language, a governing-basis clarification boundary before deep multi-branch explanation, a compact post-compact re-anchor boundary before explanation resumes after compaction, explicit support for unpacking variables/fields/config keys/internal labels before deeper reasoning, explicit deferral of continuation-vs-option policy to accurate-communication, and goal-qualified proposal framing when future ideas are offered after bounded completion |
 | [`flow-diagram-no-frame.md`](flow-diagram-no-frame.md) | Clean ASCII diagrams | Better readability |
 
 ---
@@ -234,6 +234,8 @@ for f in $RULE_FILES; do cp "$f" ~/.claude/rules/; done
 
 **📊 Active Runtime Rules: 35**
 
+Latest refinement: purpose-first communication framing now makes diagnosis, test, recommendation, proposal, and implementation-update answers say what they are doing earlier instead of burying that point in later detail.
+
 </div>
 
 ---
@@ -981,8 +983,8 @@ Personal rule set and configuration framework for Claude Code CLI.
 ---
 
 <p>
-  <b>Version</b>: 9.1 |
-  <b>Last Updated</b>: 2026-04-08 |
+  <b>Version</b>: 9.3 |
+  <b>Last Updated</b>: 2026-04-09 |
   <b>Framework</b>: Sophisticated AI Framework with Constitutional Governance
 </p>
 

TODO.md

@@ -1,11 +1,12 @@
 # Claude Code Rules - TODO
 
-> **Last Updated:** 2026-04-08
+> **Last Updated:** 2026-04-09
 
 ---
 
 ## ✅ Completed
 
+- [x] Refine purpose-first communication rules across wording, explanation, presentation, and style owners so diagnosis, test, recommendation, proposal, and implementation-update answers now expose what they are doing earlier; synchronize design/changelog/master surfaces; resync installed runtime copies; and complete a final consistency audit.
 - [x] Refine compact/post-compact governance so compacted-session continuation now re-anchors to the active objective, preserves the active frame, treats compressed-away exact detail as needs-recheck rather than silently verified truth, synchronizes master RULES artifacts, and reinstalls the touched runtime rules.
 - [x] Tighten the compact SessionStart hook into a reference-first review trigger so `systemMessage` now carries explicit `review-required` wording, `hookSpecificOutput.additionalContext` is reduced to instruction + file pointers + objective status only, `sessionstart-directive.json` records bounded directive proof, memsearch remains a later assist boundary, and patch/phase/changelog/master docs are synchronized for the completed Wave 021 refinement.
 - [x] Replace singleton compact plugin files with a session-scoped carry-forward model so `PreCompact` creates per-session `pending.json`, `precompact-context.json`, and `carry-forward-selected.json`, compact `SessionStart` injects only one resolved session’s selected carry-forward payload plus the re-anchor reminder, writes one per-session proof file, fails closed on ambiguity, and `PostCompact` prunes expired session directories plus rewrites the live index.
@@ -67,7 +68,7 @@
 ## 📋 Tasks To Do
 
 ### Current Governance Execution
-- [ ] (none)
+- [ ] Reconcile legacy phase review-state drift: `phase/SUMMARY.md` still carries historical `Implemented - Pending Review` entries for older rollout families, so repo-level execution tracking should either complete those reviews or explicitly retire the pending markers.
 
 ### Deferred Enhancements
 - [ ] Automated validation script for documentation compliance (deferred by user).
@@ -79,6 +80,7 @@
 
 | Date | Changes |
 |------|---------|
+| 2026-04-09 | Added purpose-first communication guidance so diagnosis, test, recommendation, proposal, and implementation-update answers now state what they are doing earlier across `accurate-communication`, `explanation-quality`, `answer-presentation`, and `natural-professional-communication`; synchronized design/changelog/master surfaces; and opened the bounded `phase-024` / `patch/purpose-first-communication-framing.patch.md` refinement wave. |
 | 2026-04-09 | Added rules-first-over-memory guidance so user-declared governance issues are fixed in RULES rather than being treated as memory-first problems, and extended portability guidance so reusable support/package source artifacts such as plugin-owned docs, scripts, skills, and agents stay portable by default; opened `phase-023` / `patch/rules-first-over-memory-and-portable-support-artifacts.patch.md` for the bounded refinement wave. |
 | 2026-04-08 | Added direct human-readable wording guidance so metaphor-heavy internal shorthand is no longer a good default explanation style when a direct action/result statement would be clearer; updated communication, explanation, style, and presentation owners plus opened `phase-022` / `patch/direct-human-readable-wording-over-metaphor-heavy-shorthand.patch.md` for the bounded refinement wave. |
 | 2026-04-08 | Added active-summary guidance so resolved topics may remain available for reasoning without being repeated in visible summaries by default, and narrowed startup patch posture so greenfield baseline formation now defaults to design/changelog/TODO/phase posture first unless a real existing before/after review surface or explicit user request justifies patch. |