devrites 2.3.0 → 2.4.0

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 All notable changes to DevRites are documented here. The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and DevRites adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). Releases are generated automatically by [semantic-release](https://semantic-release.gitbook.io/) from Conventional Commits on `main`.
 
+## [2.4.0](https://github.com/ViktorsBaikers/DevRites/compare/v2.3.0...v2.4.0) (2026-06-27)
+
+### Added
+
+* **devrites:** enforce the doubt gate from invocation through seal ([0397cca](https://github.com/ViktorsBaikers/DevRites/commit/0397cca2158ed1e798c29122485d4e2b69ea4f80))
+
 ## [2.3.0](https://github.com/ViktorsBaikers/DevRites/compare/v2.2.0...v2.3.0) (2026-06-23)
 
 ### Added

package/README.md

@@ -101,7 +101,7 @@ Full diagram set (lifecycle, polish orchestrator, review fan-out, debug loop,
 rules carrier, workspace state, namespace map) →
 [`docs/flow.md`](docs/flow.md).
 
-**Status:** [`v2.3.0`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v2.3.0) — see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
+**Status:** [`v2.4.0`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v2.4.0) — see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
 
 ## Contents
 

package/pack/.claude/skills/devrites-doubt/SKILL.md

@@ -19,7 +19,7 @@ code · claiming "this is safe", "this scales", or "this matches the spec".
 
 - [ ] **1. CLAIM** — state the claim in 1–3 sentences + why it matters.
 - [ ] **2. EXTRACT** — isolate the smallest reviewable artifact + its contract; strip your reasoning so the reviewer sees only the code/decision.
-- [ ] **3. DOUBT** — invoke a fresh-context reviewer with an ADVERSARIAL prompt: *"find what's wrong; do not validate."* Prefer a real subagent (`.claude/agents/devrites-doubt-reviewer`) so it has no anchoring context.
+- [ ] **3. DOUBT** — `Task` a fresh-context `devrites-doubt-reviewer` with an ADVERSARIAL prompt: *"find what's wrong; do not validate."* The subagent dispatch is **required** — doing the adversarial pass inline does **not** satisfy this step: you wrote the decision, so you are exactly the anchoring context the step exists to strip. Inline is a degraded fallback **only** when the `Task` tool is genuinely unavailable, and must be flagged as such in the verdict.
 - [ ] **4. RECONCILE** — classify EVERY finding: contract misread | valid & actionable | valid trade-off | noise.
 - [ ] **5. STOP** — met a stop condition (only trivial findings, 3 cycles done, or user override). Emit a **binary gate verdict** the orchestrator must clear: **accept** (no valid-&-actionable findings remain) or **reject + the specific required changes**. On reject, the orchestrator loops the wright on those changes before the slice is accepted; still reject after the 3-cycle cap → escalate to the user.
 

package/pack/.claude/skills/devrites-lib/scripts/doubt-coverage.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# doubt-coverage.sh — did the build doubt the decisions it stood?
+# Deterministic, zero-token. Reads the append-only footprint log the orchestrator writes at
+# /rite-build step 4 (one `doubt` line per devrites-doubt dispatch) and reports doubt coverage
+# against wright dispatches. It CANNOT prove a 1:1 verdict-per-decision match — `Decisions stood`
+# is not a structured ledger — so it proves the cheap, unambiguous half: a feature that ran the
+# wright but never once doubted a decision. The seal's prose gate (step 4a) + the reviewer fan-out
+# judge severity against decisions.md.
+#
+#   doubt-coverage.sh <slug>
+#
+# Exit: 0 = doubt dispatches present, or nothing to assess (no log / no wright) → pass.
+#       1 = wright dispatch(es) logged but ZERO doubt dispatches → coverage gap. The seal treats
+#           it as a finding (Important; NO-GO when decisions.md records an irreversible-risk
+#           decision — auth / public-API / migration — with no verdict).
+#       2 = usage.
+set -u
+
+slug="${1:-}"
+[ -n "$slug" ] || { echo "usage: doubt-coverage.sh <slug>" >&2; exit 2; }
+
+log=".devrites/work/$slug/footprint.log"
+if [ ! -f "$log" ]; then
+  echo "doubt-coverage: no footprint log — nothing to assess (pass)"
+  exit 0
+fi
+
+w=$(awk '$2=="wright"{n++} END{print n+0}' "$log")
+d=$(awk '$2=="doubt"{n++}  END{print n+0}' "$log")
+
+echo "doubt-coverage: $w wright · $d doubt"
+
+if [ "$w" -gt 0 ] && [ "$d" -eq 0 ]; then
+  echo "doubt-coverage: GAP — $w wright dispatch(es), 0 doubt dispatches. Either every slice's"
+  echo "'Decisions stood' was genuinely empty, or step-4 doubt was skipped. Confirm against"
+  echo "decisions.md before GO."
+  exit 1
+fi
+exit 0

package/pack/.claude/skills/rite-build/SKILL.md

@@ -164,7 +164,21 @@ writes; read them yourself for the doubt/record gates or in the inline fallback:
 4. **Doubt the decisions it stood up.** For each entry in the wright's `Decisions stood`
    (branching, boundary crossing, data model, auth, public API, migration, user-flow change,
    "this is safe/scales") apply `devrites-doubt` **before accepting the slice** — the writer
-   doesn't grade its own decisions. The doubt loop honours `.devrites/AFK` (see its AFK
+   doesn't grade its own decisions. Each `devrites-doubt` invocation **dispatches the
+   `devrites-doubt-reviewer` subagent** (doing the adversarial pass inline is the writer grading
+   itself — the thing this step exists to forbid). **Completion criterion (checkable):** step 4
+   is done only when **every** `Decisions stood` entry carries a recorded `devrites-doubt`
+   verdict — `accept`, or `reject` + the required changes — in `decisions.md` (accepted
+   trade-offs) / `questions.md` (open gates). A `Decisions stood` entry with **no verdict on
+   record** means doubt did not run for it: **do not enter step 5 and do not mark the slice
+   `built`.** Log each dispatch so the seal can prove doubt ran (the footprint already counts a
+   `doubt` kind):
+   ```bash
+   FP=.claude/skills/devrites-lib/scripts/footprint.sh
+   [ -f "$FP" ] || FP="${CLAUDE_SKILL_DIR:-}/../devrites-lib/scripts/footprint.sh"
+   [ -f "$FP" ] || FP=pack/.claude/skills/devrites-lib/scripts/footprint.sh
+   [ -f "$FP" ] && bash "$FP" log <slug> doubt "<decision id>" || true
+   ``` The doubt loop honours `.devrites/AFK` (see its AFK
    exception): findings below the slice's gate ceiling become advisory entries in `questions.md`;
    destructive / auth / public-API concerns always pause regardless. A non-empty `Escalation` in
    the artifact is handled here too: irreversible-risk / blockers → blocking question + set

package/pack/.claude/skills/rite-seal/SKILL.md

@@ -42,6 +42,7 @@ Read `review.md` and the latest reviewer outputs.
 | Diff violates a declared project principle (`.devrites/principles.md`) with no recorded, human-approved exception | **NO-GO**, list each violated principle with `file:line`. Same standing as an unproven criterion (absent / empty file → none declared → not a blocker). |
 | Unresolved drift in `drift.md` | **NO-GO**, route through `/rite-plan` first. |
 | Any `questions.md` entry with `gate: validating` and `status: open` | **NO-GO** regardless of behavior impact — an open validating gate is merge-blocking by definition. A slice marked `built (pending review)` is not done. |
+| `doubt-coverage` rc=1, or a stood decision (boundary / data-model / auth / public-API / migration / branching) recorded in `decisions.md` with no `devrites-doubt` verdict | **Important** — and **NO-GO** when the undoubted decision is an irreversible-risk class (auth / public-API / migration), the same standing as an unproven acceptance criterion. `/rite-build` step 4 records the verdict + logs a `doubt` footprint; absence here means doubt was skipped. Genuinely-empty `Decisions stood` on every slice is a valid pass — confirm, don't assume. |
 
 ## Workflow
 1. **Run the shared orientation preamble** — it prints `state.md`, the artifacts present,
@@ -75,6 +76,22 @@ Read `review.md` and the latest reviewer outputs.
    behavior blocks. **Any `questions.md` entry with `gate: validating` and `status: open`
    is a NO-GO regardless of behavior impact** (an open validating gate is merge-blocking by
    definition); a slice marked `built (pending review)` is not done.
+4a. **Doubt coverage — every stood decision was independently doubted.** Run the deterministic
+   check, then judge it against `decisions.md`:
+   ```bash
+   DC=.claude/skills/devrites-lib/scripts/doubt-coverage.sh
+   [ -f "$DC" ] || DC="${CLAUDE_SKILL_DIR:-}/../devrites-lib/scripts/doubt-coverage.sh"
+   [ -f "$DC" ] || DC=pack/.claude/skills/devrites-lib/scripts/doubt-coverage.sh
+   [ -f "$DC" ] && { bash "$DC" <slug>; echo "doubt-coverage rc=$?"; } || echo "(doubt-coverage gate unavailable — confirm by hand each stood decision carries a devrites-doubt verdict)"
+   ```
+   The script proves the **footprint half** (a `doubt` dispatch was logged per `/rite-build`
+   step 4); you prove the **verdict half**: every decision in `decisions.md` that crosses a doubt
+   trigger (boundary / data-model / auth / public-API / migration / branching / "safe" / "scales")
+   must carry a recorded `devrites-doubt` verdict — `accept`, or a `reject` whose required changes
+   were resolved. Per the severity gate: **rc=1 or a triggering decision with no verdict is an
+   Important finding**, escalating to **NO-GO** when the undoubted decision is irreversible-risk
+   (auth / public-API / migration). A genuinely-empty `Decisions stood` across every slice passes —
+   confirm it against `decisions.md`, don't assume it.
 5. Check **security, data, migration, rollback** risk —
    [risk-and-rollback](reference/risk-and-rollback.md). If `strategy.md` exists (from
    `/rite-temper`), confirm its **top pre-mortem risks are mitigated** in the diff/evidence and

package/pack/.claude/skills/rite-seal/reference/anti-patterns.md

@@ -16,6 +16,7 @@ see [rules/anti-patterns.md](../../../rules/anti-patterns.md).
 | "Drift is small; resolve it inline and seal." | Unresolved drift = NO-GO, no exceptions. Route through `/rite-plan` to repair, then seal. |
 | "Reviewer findings overlap; average them away." | Surface disagreements explicitly. Averaging hides where the reviewers actually disagree. |
 | "Carry the old reviewer verdicts though the diff changed." | If the diff changed since `/rite-review`, re-run the Spec + Code axes — don't carry stale verdicts forward. |
+| "Build never doubted a decision, but the wright seemed confident — GO without checking." | Doubt is a gate, not a vibe. `doubt-coverage` rc=1 — or a stood boundary / data-model / auth / public-API / migration decision in `decisions.md` with no recorded `devrites-doubt` verdict — is an Important finding, escalating to NO-GO when the undoubted decision is irreversible-risk (auth / public-API / migration). An empty `Decisions stood` on every slice passes only when confirmed against `decisions.md`, never assumed. |
 
 ## Red Flags
 
@@ -25,3 +26,4 @@ see [rules/anti-patterns.md](../../../rules/anti-patterns.md).
 - `seal.md` written before walking *every* acceptance criterion one by one.
 - A NO-GO rounded up to GO "to be agreeable".
 - Unresolved drift, unresolved questions, or pending tasks — and you're sealing anyway.
+- `doubt-coverage` rc=1 left unexamined, or a stood irreversible-risk decision (auth / public-API / migration) carrying no recorded `devrites-doubt` verdict — and you're sealing GO anyway.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "devrites",
-  "version": "2.3.0",
+  "version": "2.4.0",
   "description": "DevRites — disciplined senior-engineer workflow skills pack for Claude Code",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/ViktorsBaikers/DevRites#readme",