@tekyzinc/gsd-t 5.1.12 → 5.1.13

package/CHANGELOG.md

@@ -2,6 +2,15 @@
 
 All notable changes to GSD-T are documented here. Updated with each release.
 
+## [5.1.13] - 2026-07-15
+
+### Changed — explicit "No Preambles" rule with banned openers
+
+Simply Stated already said "no preamble," but framing phrases like "One thing I owe you honestly:" kept appearing. Added an explicit NO PREAMBLES rule that names the banned opener phrases ("One thing I owe you honestly:", "To be honest", "Here's the thing", "Full transparency:", "The key insight is", etc.) so they're caught by name — delete the opener, lead with the point.
+
+- `scripts/gsd-t-auto-route.js`: NO PREAMBLES rule + banned-opener list in `READER_CONTRACT`.
+- `templates/CLAUDE-global.md` (+ `~/.claude/CLAUDE.md`): banned openers added to the doctrine's §conversational block.
+
 ## [5.1.12] - 2026-07-13
 
 ### Changed — Simply Stated now governs conversational narration (4th enforcement layer)

package/README.md

@@ -1,6 +1,6 @@
 # GSD-T: Contract-Driven Development for Claude Code
 
-**v5.1.12** - A methodology for reliable, parallelizable development using Claude Code with optional Agent Teams support.
+**v5.1.13** - A methodology for reliable, parallelizable development using Claude Code with optional Agent Teams support.
 
 **Eliminates context rot** — task-level fresh dispatch (one subagent per task, ~10-20% context each) means compaction never triggers.
 **Compaction-proof debug loops** — `gsd-t headless --debug-loop` runs test-fix-retest cycles as separate `claude -p` sessions. A JSONL debug ledger persists all hypothesis/fix/learning history across fresh sessions. Anti-repetition preamble injection prevents retrying failed hypotheses. Escalation tiers (sonnet → opus → human) and a hard iteration ceiling enforced externally.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tekyzinc/gsd-t",
-  "version": "5.1.12",
+  "version": "5.1.13",
   "description": "GSD-T: Contract-Driven Development for Claude Code — 54 slash commands with headless-by-default workflow spawning, unattended supervisor relay with event stream, graph-powered code analysis, real-time agent dashboard, task telemetry, doc-ripple enforcement, backlog management, impact analysis, test sync, milestone archival, and PRD generation",
   "author": "Tekyz, Inc.",
   "license": "MIT",

package/scripts/gsd-t-auto-route.js

@@ -32,6 +32,7 @@ const path = require("path");
 const READER_CONTRACT = [
   "[GSD-T READER CONTRACT] Before sending ANY reply, assume your first draft is too wordy and rewrite it tight. Rules:",
   "• Answer FIRST. No preamble, no restating the question, no narrating what you're about to do (\"let me check…\"). Do the work silently, then give the result.",
+  "• NO PREAMBLES — start with the answer, never a framing phrase. BANNED openers (and anything like them): \"One thing I owe you honestly:\", \"To be honest\", \"Here's the thing\", \"The honest truth is\", \"I'll be straight with you\", \"Let me level with you\", \"Full transparency:\", \"Real talk\", \"What's worth noting here\", \"The key insight is\", \"Here's what's happening\". Delete the opener and lead with the actual point — if a sentence only announces that a point is coming, cut it.",
   "• Exception — when you're about to CHANGE code/files: state intent in one line first, so the user can stop a wrong direction.",
   "• Gloss every code/jargon term in plain words on first use. No bare IDs or acronyms the reader must decode.",
   "• Bullets/tables over paragraphs. Cut hedging and meta-commentary. Expand only if asked.",

package/templates/CLAUDE-global.md

@@ -484,7 +484,7 @@ See memory pointer: `feedback_auto_research_external_gaps`.
 
 **The HALT (the teeth):** a deliverable whose simply-stated lead cannot be written cleanly is NOT done — stop, surface it, re-think the muddled part. Do not ship the verbose version with an apology; the verbose version is evidence the design has a gap.
 
-**§Applies to conversational narration too, not just formal deliverables.** The doctrine governs REPLIES and mid-work talk-to-the-user, not only architectures/plans/findings. Two extra rules there: **NO PREAMBLE** (no throat-clearing, no "let me…", no narrating-the-explanation like "it matters that I say why…" — give the point, not a description of the point), and **load-bearing point FIRST** (never buried after justification clauses). No clever phrase that obscures where a plain one is clearer.
+**§Applies to conversational narration too, not just formal deliverables.** The doctrine governs REPLIES and mid-work talk-to-the-user, not only architectures/plans/findings. Two extra rules there: **NO PREAMBLES** (no throat-clearing, no "let me…", no narrating-the-explanation like "it matters that I say why…" — give the point, not a description of the point; BANNED openers and anything like them: "One thing I owe you honestly:", "To be honest", "Here's the thing", "The honest truth is", "I'll be straight with you", "Full transparency:", "What's worth noting", "The key insight is" — delete the opener, lead with the point), and **load-bearing point FIRST** (never buried after justification clauses). No clever phrase that obscures where a plain one is clearer.
 
 **§Enforcement (four layers):** (1) this doctrine = the definition; (2) the **Architect's Oversight Write/Edit trigger** carries a Simply-Stated line; (3) the **plan/milestone Six-Stage Pass + `/gsd-t-architect` gain a Simply-Stated gate** — the pass does not complete until its finding/plan has a clean simply-stated lead, and the validation protocols flag a deliverable that lacks one (a REQUIRED ARTIFACT like the pseudocode file, not advice); (4) the **every-turn Reader Contract** (injected by the UserPromptSubmit hook `scripts/gsd-t-auto-route.js`) carries the Simply-Stated rule + a before/after example, so it governs conversational output each reply — the channel that reaches mid-work narration, which layers 2-3 do not.