baseline-precheck
Skill16 starsChanged yesterdayApache-2.0View on GitHub
実装前 pytest baseline を deterministic に測定・構造化し、workflow verdict を返す。
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- grill-meSkill
- herdr-kaji-launchSkill
- i-dev-final-checkSkill
- i-doc-final-checkSkill
- i-doc-fixSkill
- i-doc-reviewSkill
- i-doc-updateSkill
- i-doc-verifySkill
- incident-cycleSkill
- incident-fixSkill
- incident-investigateSkill
- incident-reportSkill
- incident-reviewSkill
- incident-verifySkill
- i-prSkill
- issue-closeSkill
- issue-createSkill
- issue-designSkill
- issue-fix-codeSkill
- issue-fix-designSkill
- issue-fix-readySkill
- issue-implementSkill
- issue-review-codeSkill
- issue-review-designSkill
- issue-review-readySkill
- issue-small-change-executeSkill
- issue-small-change-reviewSkill
- issue-startSkill
- issue-verify-codeSkill
- issue-verify-designSkill
- kaji-run-verifySkill
- pr-fixSkill
- pr-verifySkill
- releaseSkill
- release-starterSkill
- review-cycleSkill
- review-pollSkill
- reviewSkill
- review-starter-updateSkill
- run-watchedSkill
- series-createSkill
- update-starterSkill
- watch-triageSkill
The file
Files
Baseline Precheck
設計レビュー PASS 後、実装開始前に agent を起動せず pytest baseline を一度測定する。
入力
KAJI_WORKTREE_DIR: 測定対象 worktreeKAJI_ISSUE_ID: 証跡コメントの投稿先KAJI_BRANCH_NAME: artifact に記録する branchKAJI_GIT_REMOTE/KAJI_DEFAULT_BRANCH: 実装 commit 判定の基点<KAJI_GIT_REMOTE>/<KAJI_DEFAULT_BRANCH>(remote 側の default branch。ローカルの default branch は使わない)KAJI_VERDICT_PATH: pure YAML verdict の保存先
出力
構造化 artifact の正本は
[worktree]/.kaji-artifacts/baseline/baseline.json。clean / known_failures は
PASS、blocked / invalid は ABORT を返す。基点 ref が解決できない場合は artifact を作らず
baseline_base_ref_unresolvable で ABORT する。詳細ポリシーは
docs/dev/baseline-check.md を参照する。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

