devrites 6.8.0 → 6.8.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (9) hide show
  1. package/CHANGELOG.md +6 -0
  2. package/README.md +1 -1
  3. package/pack/.claude/skills/rite-autocomplete/reference/stop-conditions.md +6 -1
  4. package/pack/generated/claude/skills/rite-autocomplete/reference/stop-conditions.md +6 -1
  5. package/pack/generated/codex/skills/rite-autocomplete/reference/stop-conditions.md +6 -1
  6. package/pack/generated/devin/skills/rite-autocomplete/reference/stop-conditions.md +6 -1
  7. package/pack/generated/omp/skills/rite-autocomplete/reference/stop-conditions.md +6 -1
  8. package/pack/generated/pi/skills/rite-autocomplete/reference/stop-conditions.md +6 -1
  9. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -2,6 +2,12 @@
2
2
 
3
3
  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`.
4
4
 
5
+ ## [6.8.1](https://github.com/ViktorsBaikers/DevRites/compare/v6.8.0...v6.8.1) (2026-10-18)
6
+
7
+ ### Fixed
8
+
9
+ * **devrites:** a first seal NO-GO recovers before it stops ([#130](https://github.com/ViktorsBaikers/DevRites/issues/130)) ([17c1340](https://github.com/ViktorsBaikers/DevRites/commit/17c1340ec4e30307f56948a8a1e86480224a198c))
10
+
5
11
  ## [6.8.0](https://github.com/ViktorsBaikers/DevRites/compare/v6.7.4...v6.8.0) (2026-10-18)
6
12
 
7
13
  ### Added
package/README.md CHANGED
@@ -31,7 +31,7 @@ history can't lose it. After you clear the conversation, switch hosts, or hand
31
31
  the feature to another engineer, the next session reads the same plan,
32
32
  decisions, and evidence before it continues.
33
33
 
34
- **Status:** [`v6.8.0`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v6.8.0): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
34
+ **Status:** [`v6.8.1`](https://github.com/ViktorsBaikers/DevRites/releases/tag/v6.8.1): see [`CHANGELOG.md`](CHANGELOG.md) for release notes.
35
35
 
36
36
  This is the latest published release; `main` may contain unreleased work.
37
37
 
package/pack/.claude/skills/rite-autocomplete/reference/stop-conditions.md CHANGED
@@ -77,7 +77,12 @@ class or park; only a real human/risk/scope gate stops for a human.
77
77
  - **Seal:** remaining NO-GO after recommended-option questions are closed, with
78
78
  every remaining blocker and fix direction. Never round up to GO. An open
79
79
  recommended-option blocking question is not a Seal stop: resolve it, recover
80
- agent-owned findings, then re-enter Seal.
80
+ agent-owned findings, then re-enter Seal. A first NO-GO is not a stop either:
81
+ recover every agent-owned blocker (missing or unbound proof, a reviewer gap root
82
+ can close, a finding with a fix direction, a missing `review.md` verdict), then
83
+ re-enter Seal. The unattended `N` to accepting Important risks means repair, not
84
+ stop. Stop only for blockers that need a human: accepting a risk, changing scope
85
+ or an acceptance criterion, or access. Record each one as a question.
81
86
  - **Reslice:** execute its marked action before deciding continue/stop.
82
87
  - **Slice budget:** do not stop on `--max-slices`. Leftover
83
88
  pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
package/pack/generated/claude/skills/rite-autocomplete/reference/stop-conditions.md CHANGED
@@ -79,7 +79,12 @@ class or park; only a real human/risk/scope gate stops for a human.
79
79
  - **Seal:** remaining NO-GO after recommended-option questions are closed, with
80
80
  every remaining blocker and fix direction. Never round up to GO. An open
81
81
  recommended-option blocking question is not a Seal stop: resolve it, recover
82
- agent-owned findings, then re-enter Seal.
82
+ agent-owned findings, then re-enter Seal. A first NO-GO is not a stop either:
83
+ recover every agent-owned blocker (missing or unbound proof, a reviewer gap root
84
+ can close, a finding with a fix direction, a missing `review.md` verdict), then
85
+ re-enter Seal. The unattended `N` to accepting Important risks means repair, not
86
+ stop. Stop only for blockers that need a human: accepting a risk, changing scope
87
+ or an acceptance criterion, or access. Record each one as a question.
83
88
  - **Reslice:** execute its marked action before deciding continue/stop.
84
89
  - **Slice budget:** do not stop on `--max-slices`. Leftover
85
90
  pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
package/pack/generated/codex/skills/rite-autocomplete/reference/stop-conditions.md CHANGED
@@ -79,7 +79,12 @@ class or park; only a real human/risk/scope gate stops for a human.
79
79
  - **Seal:** remaining NO-GO after recommended-option questions are closed, with
80
80
  every remaining blocker and fix direction. Never round up to GO. An open
81
81
  recommended-option blocking question is not a Seal stop: resolve it, recover
82
- agent-owned findings, then re-enter Seal.
82
+ agent-owned findings, then re-enter Seal. A first NO-GO is not a stop either:
83
+ recover every agent-owned blocker (missing or unbound proof, a reviewer gap root
84
+ can close, a finding with a fix direction, a missing `review.md` verdict), then
85
+ re-enter Seal. The unattended `N` to accepting Important risks means repair, not
86
+ stop. Stop only for blockers that need a human: accepting a risk, changing scope
87
+ or an acceptance criterion, or access. Record each one as a question.
83
88
  - **Reslice:** execute its marked action before deciding continue/stop.
84
89
  - **Slice budget:** do not stop on `--max-slices`. Leftover
85
90
  pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
package/pack/generated/devin/skills/rite-autocomplete/reference/stop-conditions.md CHANGED
@@ -79,7 +79,12 @@ class or park; only a real human/risk/scope gate stops for a human.
79
79
  - **Seal:** remaining NO-GO after recommended-option questions are closed, with
80
80
  every remaining blocker and fix direction. Never round up to GO. An open
81
81
  recommended-option blocking question is not a Seal stop: resolve it, recover
82
- agent-owned findings, then re-enter Seal.
82
+ agent-owned findings, then re-enter Seal. A first NO-GO is not a stop either:
83
+ recover every agent-owned blocker (missing or unbound proof, a reviewer gap root
84
+ can close, a finding with a fix direction, a missing `review.md` verdict), then
85
+ re-enter Seal. The unattended `N` to accepting Important risks means repair, not
86
+ stop. Stop only for blockers that need a human: accepting a risk, changing scope
87
+ or an acceptance criterion, or access. Record each one as a question.
83
88
  - **Reslice:** execute its marked action before deciding continue/stop.
84
89
  - **Slice budget:** do not stop on `--max-slices`. Leftover
85
90
  pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
package/pack/generated/omp/skills/rite-autocomplete/reference/stop-conditions.md CHANGED
@@ -79,7 +79,12 @@ class or park; only a real human/risk/scope gate stops for a human.
79
79
  - **Seal:** remaining NO-GO after recommended-option questions are closed, with
80
80
  every remaining blocker and fix direction. Never round up to GO. An open
81
81
  recommended-option blocking question is not a Seal stop: resolve it, recover
82
- agent-owned findings, then re-enter Seal.
82
+ agent-owned findings, then re-enter Seal. A first NO-GO is not a stop either:
83
+ recover every agent-owned blocker (missing or unbound proof, a reviewer gap root
84
+ can close, a finding with a fix direction, a missing `review.md` verdict), then
85
+ re-enter Seal. The unattended `N` to accepting Important risks means repair, not
86
+ stop. Stop only for blockers that need a human: accepting a risk, changing scope
87
+ or an acceptance criterion, or access. Record each one as a question.
83
88
  - **Reslice:** execute its marked action before deciding continue/stop.
84
89
  - **Slice budget:** do not stop on `--max-slices`. Leftover
85
90
  pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
package/pack/generated/pi/skills/rite-autocomplete/reference/stop-conditions.md CHANGED
@@ -79,7 +79,12 @@ class or park; only a real human/risk/scope gate stops for a human.
79
79
  - **Seal:** remaining NO-GO after recommended-option questions are closed, with
80
80
  every remaining blocker and fix direction. Never round up to GO. An open
81
81
  recommended-option blocking question is not a Seal stop: resolve it, recover
82
- agent-owned findings, then re-enter Seal.
82
+ agent-owned findings, then re-enter Seal. A first NO-GO is not a stop either:
83
+ recover every agent-owned blocker (missing or unbound proof, a reviewer gap root
84
+ can close, a finding with a fix direction, a missing `review.md` verdict), then
85
+ re-enter Seal. The unattended `N` to accepting Important risks means repair, not
86
+ stop. Stop only for blockers that need a human: accepting a risk, changing scope
87
+ or an acceptance criterion, or access. Record each one as a question.
83
88
  - **Reslice:** execute its marked action before deciding continue/stop.
84
89
  - **Slice budget:** do not stop on `--max-slices`. Leftover
85
90
  pre-existing remaining value, explicit flag, sentinel cap, or post-vet pending count
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "devrites",
3
- "version": "6.8.0",
3
+ "version": "6.8.1",
4
4
  "description": "DevRites: a disciplined senior-engineer workflow pack for Claude Code, Codex, omp, pi, and Devin CLI",
5
5
  "license": "SEE LICENSE IN LICENSE",
6
6
  "homepage": "https://github.com/ViktorsBaikers/DevRites#readme",