[jammyfu]

What

Aligns github-risers with the owner's CoderSkills harness (jammyfu/CoderSkills @ d37305a). Plan and governance files were stale after the rebrand, and the loop rules lived only in chat. No change to rankings, categories, the ⚠ suspected-crack rules, translations (tools/i18n.py, data/translation_library.json), GEO files or the slim README. No generated file is touched.

Skills used (with paths)

Skill	Path in CoderSkills	How it was used
continuous-project-loop	skills/continuous-project-loop/SKILL.md	standard file set, one plan entry, Assess→Plan→Implement→Verify→Record→Continue, planning rules (one Goal, 3-7 tasks, Out of Scope, Next Candidates), verification hardening and regression rules, dirty-worktree rule written into repo files
multi-project-program-management	skills/multi-project-program-management/SKILL.md	standard docs (AUTOMATION_COMMANDS, LONG_RUNNING_AUTONOMY), thin README with doc references (audited, already true), plan/governance refresh
readme-tech-visualizer	skills/readme-tech-visualizer/SKILL.md	audit only: README first screen has no runtime/dependency table or "Generated by" noise; no hero/badge block generated (the header image belongs to the GEO work)

Not applicable (read, not used): skills/git-autosync-signal (supports only dramaforge and clippipeline), skills/skill-lab-builder, skills/jammyfu-laodeng and the content/media skills. The safe-sync tooling (sync_or_queue.py) is not adopted: this repo changes through PRs and only the daily job writes data.

Changed files

• CURRENT_PLAN.md (PLAN-001), MASTER_PLAN.md, TODO_BACKLOG.md: rewritten to the current state
• docs/project-governance/{WORKLOG,DECISIONS,ACCEPTANCE,CHANGELOG}.md: records for feat: rebrand to github-risers with multi-category rankings #6-feat: translation library + glossary, slim README (top 10, first screen) #10 and this round, Phase 3/4 acceptance
• AGENTS.md, docs/LONG_RUNNING_AUTONOMY.md, docs/AUTOMATION_COMMANDS.md: loop order, dirty-worktree rule, record list, verify hardening, next_plan.py --check
• tools/next_plan.py: --check (planning rules), roll() takes a root for tests
• tools/local_daily.sh: exports RISERS_DAILY_RUN=1 so doc-state tests never block a data update
• tests/test_harness.py (new, 14 tests): required files, AGENTS/doc rules, plan shape, rolling behaviour, verify.py and local_daily.sh PATH/shell=True hardening, update→verify→commit order

Constraints kept

Zero telemetry (existing test passes); data only from the GitHub API (no data file touched); ⚠ suspected-crack rules unchanged; no translations added or changed.

Verification

python3 tools/verify.py            # All verification commands passed (173 tests)
python3 tools/next_plan.py --check # CURRENT_PLAN.md follows the planning rules.
GITHUB_EVENT_NAME=schedule python3 -m unittest tests.test_harness   # doc checks skipped in the daily run

Do not merge without the owner's approval.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-10-30T11:27:37.301607Z	1a915c4	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.