From tend-ci-runner
Hourly analysis of Claude CI session logs — identifies behavioral problems, skill gaps, and workflow issues.
npx claudepluginhub max-sixty/tend --plugin tend-ci-runnerThis skill uses the workspace's default tool permissions.
Analyze Claude-powered CI runs from the past hour. Identify behavioral problems, skill gaps, and
Daily review of the previous night's CI runs — identifies problems and improves repo-local skills and workflows.
Debugs Claude CI runs by downloading and parsing session log artifacts from GitHub Actions. Use when asked to "debug a CI run", "check what the bot did", "look at session logs", "investigate a tend run", "why did the bot do X", "what happened in CI", or to trace bot behavior in a specific workflow run.
Orchestrates periodic repository review cycles: dispatches specialized reviewers for API contracts/docs/code/skills, aggregates findings, escalates to reports/issues/PRs.
Share bugs, ideas, or general feedback.
Analyze Claude-powered CI runs from the past hour. Identify behavioral problems, skill gaps, and workflow issues — then create PRs or issues to fix them.
Target repo: $ARGUMENTS
Analysis targets an adopter repo whose CI runs are analyzed. Findings result in PRs/issues on the current repo (tend) to improve skills and workflows.
Use -R $ARGUMENTS for commands that access the target repo (downloading artifacts, querying runs
and PRs). Commands without -R default to tend.
@review-gates.md
Use TRACKING_LABEL="review-reviewers-tracking" for this skill's tracking issues. Use
-R $ARGUMENTS when downloading session logs for historical evidence verification.
List recently completed Claude CI runs on the target repo:
TARGET_REPO=$ARGUMENTS ${CLAUDE_PLUGIN_ROOT}/scripts/list-recent-runs.sh
The script discovers tend-* workflows by default. Pass additional prefixes as arguments to
include other workflows (e.g., review-reviewers when analyzing tend itself).
If empty, report "no runs to review" and exit.
Load /install-tend:debug-ci-session for download commands and JSONL parsing queries. Use
-R $ARGUMENTS for all gh commands targeting the adopter repo.
Skip runs without artifacts. Trace decision chains: what did Claude decide, what evidence did it use, what was the outcome?
For tend-review runs, compare what the bot said against what happened next:
HEAD_BRANCH=$(gh -R $ARGUMENTS run view <run-id> --json headBranch --jq '.headBranch')
PR_NUMBER=$(gh -R $ARGUMENTS pr list --head "$HEAD_BRANCH" --state all --json number --jq '.[0].number')
Check for subsequent commits that undid something the bot approved (gap in review), and human review comments flagging issues the bot missed. Pull in the full PR context — not just changes from the past hour.
CI polling time is expected and acceptable — do not flag it.
Before creating issues or PRs, check exhaustively for existing ones:
gh issue list --state open --label claude-behavior --json number,title,body
gh issue list --state open --json number,title,body # also check unlabeled issues
gh pr list --state open --json number,title,headRefName,body
gh issue list --state closed --label claude-behavior --json number,title,closedAt --limit 30
Search titles AND bodies for related keywords. Only comment on existing issues if you have material new cases that would change the approach or increase prioritization. Do not comment with progress updates, fix-PR status, or re-statements of evidence already in the issue.
Prefer PRs over issues. A PR with a clear description is immediately actionable.
hourly/review-$GITHUB_RUN_ID, fix, commit, push, create with label
claude-behavior. Put full analysis in PR description (run ID, log excerpts, root cause, gate
assessment including historical evidence count). Don't also create a separate issue.Group multiple findings by broad theme. Limit to at most 2 PRs per run — if you have more findings, pick the highest-confidence ones and note the rest in the tracking issue.
If no problems found (or none passed the gates), report "all clear" with: runs analyzed, sessions reviewed, brief quality assessment, and any below-threshold findings recorded in the tracking issue.