agent-squad-hr

Resolve rebase/merge conflicts in the the-project-repo repo when an old PR is being merged into a much-newer main. Use when: (1) `git rebase origin/main` or `git merge origin/main` reports CONFLICTs limited to `docs/generate_tracker.py`, `docs/site/index.html`, `docs/site/roadmap.html`, `docs/site/active-sprint.html`, or `docs/site/assets/site.{css,js}`, (2) you are cleaning up stale PRs authored in earlier sessions, (3) an add/add conflict appears in `docs/overnight/<date>/state/*.json` or `docs/handoffs/session_NNN_*.md` because both branches wrote the same session artefact. Covers the "union the generator, regenerate the HTML" playbook discovered while clearing 12 open PRs in Session 102. v1.3.0 (2026-05-08) adds Step 2a (ID-collision: your Item() ID claimed on main → renumber to next free ID + propagate rename to PR body / commit msgs / handoff) and Step 2b (recurring-rebase loop in dense parallel-PR windows, with `gh pr merge --auto` footgun warning for solo-contributor repos without required-status-check branch protection). v1.4.0 (2026-05-08, an earlier session) adds Step 2c (silent ID collision: two Items with same ID at different file positions produce NO rebase conflict but still collide logically; audit via `grep -c | sort | uniq -c | sort -rn` post-rebase AND post-merge — the id-fn favicon-vs-an earlier session-retro case where collision was only caught in the next session's handoff PR via `wc -l` audit, not at rebase time).

Recover gracefully when an Anthropic credit/billing failure stalls multiple in-flight parallel subagents mid-orchestration, then later resolves. Use when: (1) you've dispatched 2+ parallel subagents (Task tool with `run_in_background: true`) and a credit/billing issue, MCP outage, or other transient harness failure has frozen them, (2) the user reports the issue is now resolved and asks you to continue, (3) you're about to relaunch "resume" agents to pick up where stalled originals left off. Defends against the silent-revive trap: when API access is restored, ORIGINAL stalled subagents can auto-resume from where they froze and continue working IN PARALLEL with any "resume" agents you dispatch — leading to two agents racing on the same branch / PR / files, duplicate review comments, or one agent overwriting the other's work. Captures the diagnostic recipe (JSONL mtime + worktree-state inspection, NOT just agent status) and the safe resume pattern (state-aware briefs that detect current state and pivot to value-add if originals already recovered). Sister skill to `subagent-reports-complete-but-pr-unmerged` (different gap: completed status vs unmerged PR) and `anthropic-credit-balance-error-vs-app-bug` (different layer: diagnosing fake vs real credit errors, not recovering from real ones).

Diagnose "I edited the template / view / CSS but Flask debug-mode keeps serving the old version" when running a local dev server (Flask, Django runserver, Rails server, etc.) from one git worktree while editing files in a sibling worktree of the same repo. Use when: (1) you have multiple `git worktree` checkouts of the same repo (typical with `.claude/worktrees/<feature>` directories), (2) a dev server is running in worktree A serving its working tree, (3) you're making edits in worktree B because branch X is checked out at A and you can't `git checkout X` in B too, (4) `curl http://127.0.0.1:PORT/page` returns byte-identical responses despite your edits, (5) you're tempted to blame Jinja bytecode cache, Flask `@_ttl_cache`, or browser caching. Root cause is filesystem-level: each git worktree has its own independent working tree on disk; Flask is reading worktree A's files, not worktree B's. Cache-busting tricks (`touch app.py`, browser hard refresh, restart Flask) won't help. Sister skill to `flask-debug-ttl-cache-stale-after-rebake` (genuine TTL cache trap) and `gh-pr-merge-worktree-checkout-trap` (branch-checked-out-elsewhere errors). Different from `deploy-from-stale-worktree-silent-rollback` (which covers Cloud Run / Docker production deploys, not localhost).

Coordinate GitHub issue pickup across parallel Claude Code sessions (or human + agent) using BOTH `assignees` and a `wip` label, so sibling sessions detect the claim and skip. Use BEFORE writing any code that closes / addresses a GitHub issue when there's any chance another session is working the same repo. Trigger on phrases like "pick up issue

Diagnose and bypass `gh pr merge --squash --delete-branch` failing with "failed to run git: fatal: 'main' is already used by worktree at ..." when another git worktree has main checked out. Use when: (1) you run gh pr merge and see this exact error, (2) you have multiple worktrees in the repo (e.g. `.claude/worktrees/*`), (3) the error appears even though the GitHub merge itself looks fine. The merge SUCCEEDED on GitHub — only gh's local-side effect (post-merge `git checkout main`) failed. Verify via `gh pr view N --json state,mergedAt`; if state=MERGED, you're done. This also applies to `gh pr checkout` and any other `gh` subcommand that tries to touch the local main branch while another worktree has it claimed.