Skip to content

docs(retrospective): 2026-05-21..25 multi-day sprint retrospective#898

Merged
s977043 merged 1 commit into
mainfrom
docs/retrospective-2026-05-sprint
May 25, 2026
Merged

docs(retrospective): 2026-05-21..25 multi-day sprint retrospective#898
s977043 merged 1 commit into
mainfrom
docs/retrospective-2026-05-sprint

Conversation

@s977043

@s977043 s977043 commented May 25, 2026

Copy link
Copy Markdown
Owner

Summary

Persist the 5-day sprint retrospective as a durable doc. The sprint shipped 35 PRs / 6 releases / 1 production CVE close, and the most important lesson — per Codex's analysis — is not about velocity, but about stop conditions:

最大の問題は速度ではなく、停止条件の弱さ。次は「作る量」より「どこから保留に戻すか」を先に設計すべき。

This PR is PR 1 of 3 in the retrospective follow-up:

  1. This PR: persist the retrospective itself as docs/development/retrospectives/2026-05-21-25.md.
  2. Next PR: S3 — skills/registry.yaml community section / recommended: false flag (decide which community skills are experimental).
  3. Next PR: W1+W5 — release-please kick automation (workflow_dispatch + supporting script).

Doc structure

  • Numerical summary (35 PR / 6 release / 4 community skills / 7 dependabot bumps / 1 CVE)
  • 5 What-worked items, 6 What-didn't-work items, 3 Surprises
  • 5 Pivot Points timeline (where direction should have changed but didn't)
  • Improvement priorities split into Skills / Agents / Workflow with P0/P1/P2 ranking
  • Stop-on-Stop-Judge operational rule: Continue / Consult / Park 3-bucket classification
  • Post-hoc classification of this sprint's 35 PRs against the buckets (~13 fell into Park)
  • Next sprint opening checklist

Key proposals carried by this doc

Domain P0
Skills S3: registry.yaml community section / recommended: false flag
Agents A2: Stop-on-stop-judge guard
Workflow W1+W5: release-please kick automation

Test plan

  • markdownlint + prettier + dashes green
  • CI green

No code change. Pure documentation.

🤖 Generated with Claude Code

Capture the 5-day sprint (35 PR, 6 release, 1 production CVE close)
as durable record before starting the next session. Codex consultation
was the foundation; the primary takeaway is:

  > 最大の問題は速度ではなく、停止条件の弱さ。次は「作る量」
  > より「どこから保留に戻すか」を先に設計すべき。

Sections
- Numerical summary
- What worked (5 items: multi-perspective review, silent-skip thread,
  memory persistence, gh-api recovery, dogfood detection)
- What didn't work (6 items: overproduction past Codex stop, eval-less
  skill increase, manual release-please kick x4, AGENTS.md pollution,
  reviewer mis-suggestions, single-shot multi-perspective)
- Surprises (npm pack audit findings, CLI boundary, fs-loss recovery)
- 5 pivot points (timeline of where direction should have changed)
- Codex 100-char summary on the sprint
- Improvement priorities split into Skills / Agents / Workflow with
  P0/P1/P2 ranking
- Stop-on-stop-judge operational rule with Continue / Consult / Park
  buckets, plus post-hoc classification of this sprint's 35 PRs
  (Continue: A2-fix and CVE-class items; Consult: skill registry
  decisions; Park: ~13 PRs of docs-about-docs / marginal polish)
- Next sprint opening checklist

No code change. Foundation for two follow-up PRs (S3 registry section,
W1+W5 release-please kick automation).

Refs: Codex consultations during the 5-day sprint (PR #860 78→91,
PR #864 dogfood, PR #877 riskAssessment, post-stop 13 PRs).

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
@vercel

vercel Bot commented May 25, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
ai-review-kit Ready Ready Preview, Comment May 25, 2026 2:19am

@github-actions

Copy link
Copy Markdown
Contributor

No changes to review compared to main.

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a retrospective document for the multi-day sprint from 2026-05-21 to 2026-05-25, detailing metrics, successes, failures, and future improvement priorities. The review feedback identifies inconsistencies in the PR reclassification table, specifically regarding overlapping PR ranges and inconsistent punctuation usage.

Comment on lines +101 to +103
| Continue (やるべきだった) | #860 (concept), #861 (B'), #864 (A2-1), #865 (A2-fix-1), #869 (A2-fix-2), #871 (A2-fix-3), #877 (A2-fix-4), #888 (CVE), #896 (risk-map example), #897 (smoke runbook) |
| Consult (相談を挟むべきだった) | #862-#874 (release-please の手動 kick が繰り返された)、#873 / #875 / #881 / #884 (community skill 増産) |
| Park (本来後送りで良かった) | #866 (docs D2+D3 — 統合可能だった), #872 (docs cleanup), #887 (agent-learnings entry), #889 (README drift)、#883 (eng-practices mapping) |

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

「このスプリントの再分類」テーブルにおいて、PR番号の指定方法と区切り文字の整合性に改善の余地があります。\n\n1. 分類の重複と範囲指定: Consult 行の #862-#874 という範囲には、Continue 行にある #864, #865, #869, #871Park 行にある #866, #872 が含まれており、分類が重複しています。また、#873 が範囲内と個別の両方でリストされています。事後評価の正確性を期すため、範囲指定を避け、各バケットに属する PR を明確にリストアップすることをお勧めします。\n2. 区切り文字の統一: カンマ(,)と読点()が混在しています(例:103行目の #889 (README drift)、#883)。文書内の他のリスト(101行目や110行目など)に合わせて、カンマに統一することをお勧めします。

@github-actions

Copy link
Copy Markdown
Contributor

PlanGate Review

  • decision: pass
  • plan status: skipped-by-label
  • exec status: skipped-by-label

PlanGate review decision: pass

severity count policy
critical 0 fail
major 0 fail-if-required / warn
minor 0 comment-only
info 0 skipped

ポリシー: critical=fail / major=fail-if-required (warn) / minor=comment-only / info=skipped — spec: pages/reference/cli-review-plan-spec.md

@s977043 s977043 merged commit 51d753a into main May 25, 2026
19 checks passed
s977043 added a commit that referenced this pull request May 25, 2026
#902)

Follow-up to multi-perspective review (Self/Codex/Gemini) of PR #898-#900.
3 convergent defects fixed in one PR per Codex's process-hardening grouping.

A. release-please-kick.yml: add concurrency guard (group: release-please-kick)
   - prevents double-click 422 race on PATCH refs

B. branch input default: blank → auto-detect via gh pr list
   - eliminates silent 404 if release-please component changes
   - applied to both workflow and scripts/release-please-kick.sh

C. retrospectives/2026-05-21-25.md: add reopen conditions
   - 4 explicit triggers (new info / explicit scope / risk down / time+observation)
   - "対応を自律的に進めて" is re-judgment trigger, not auto-release
   - allowed-in-Stop list + 3-step release procedure
s977043 added a commit that referenced this pull request May 28, 2026
Direct follow-up to retrospectives/2026-05-21-25.md. Captures 27 PRs / 10
releases / 3 issues closed (#906 / #911 / #868) / 4 issues opened (#906 /
#911 / #921 / #929) / 8+ Stop-on-Stop-Judge invocations.

Key findings:
- Codify-then-validate caught its own gap in same session (#898#902)
- Multi-perspective review found convergent defects (#902)
- Stop-on-Stop-Judge stress-tested and held under 8+ autonomous prompts
- GITHUB_TOKEN no-recursion was a same-session defect (#906) that
  3-perspective review missed
- "Posture, not progress" guard rejected hand-written goldens multiple times
- Issue carve-out (#921, #929) enabled graceful epic closure

New improvement priorities:
- A8: gh-actions-privileges line in Code-gen self-review (catches #906 class)
- A9: cached-Codex-judgment heuristic (cap consults on repeated situations)
- A10: pre-merge dist rebuild for src/cli.mjs (prevents #917 class)
- W7: gh release-ratchet helper (10/27 PRs were releases)

Stop-on-Stop-Judge upheld; ~3 PRs of "stop weakness" surface vs ~13 in prior
sprint. Rule helped.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant