git:20261114.9250d3a to git:20261116.b578ddb

8 added, 6 removed. Audit A to A.

What this update changes in the checks

No check changed: every fixed check gives the same answer before and after this update.

A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.

---
name: long-run-tips
- description: "Long runs · 19 tips: multi-agent roles, progress dashboards, handoffs, remote workflows."
+ description: "Long runs · 21 tips: multi-agent roles, progress dashboards, handoffs, remote workflows."
disable-model-invocation: true
---
- # Long runs · 19 tips
+ # Long runs · 21 tips
- Copybook's 19 tips on long runs, most saved first. Each tip's text, where it goes and what the user should get are in its file in references/.
+ Copybook's 21 tips on long runs, most saved first. Each tip's text, where it goes and what the user should get are in its file in references/.
- If the user names a tip, use that tip. If they describe a task, choose the tip that best meets their goal and constraints from those that work with the agent doing the work. If several fit equally well, choose one. Tell the user in one sentence which tip you picked and why, then read its file and follow it. If another tip also fits and would materially change the approach or result, name it and say how it differs.
- If the user said nothing, show them the list below (each tip's name and what it does) and ask which to use.
- - If none fits, say so and suggest copybook, which looks through all 134 tips.
+ - If none fits, say so and suggest copybook, which looks through all 138 tips.
| Tip | What it does |
| --- | --- |
| [Progress dashboard subagent for long tasks](references/progress-dashboard-subagent.md) `progress-dashboard-subagent` | Where a long task stands while you wait: an HTML dashboard of progress, blockers and open questions, built by a side subagent. |
| [Week calendar from Claude Code sessions](references/week-calendar-from-sessions.md) `week-calendar-from-sessions` | A week of sessions you can't recall: local logs as an HTML calendar, no-commit sessions flagged, and a 3-line weekly report. |
| [Grok Bot team of 6 roles](references/grok-bot-team-of-6-roles.md) `grok-bot-team-of-6-roles` | Which work deserves its own Bot: six roles with ownership, handoffs and limits, and what stays a Skill or a routine. |
- | [Later items from your last 20 sessions](references/later-items-from-20-sessions.md) `later-items-from-20-sessions` | What you said you'd do later and forgot: past sessions searched, items ranked, each one a card that opens its own session. |
+ | [Later items from your last 20 Claude Code sessions](references/later-items-from-20-sessions.md) `later-items-from-20-sessions` | What you said you'd do later and forgot: past sessions searched, items ranked, each one a card that opens its own session. |
| [Herdr app: Opus 5.5 coordinating workers](references/herdr-app-opus-5-5-coordinates.md) `herdr-app-opus-5-5-coordinates` | Running more agents without leaving Claude Code: Opus 5.5 coordinates up to 10 workers through Herdr, and a Codex worker reviews. |
| [7 role prompts from idea to done](references/7-role-prompts-from-idea-to-done.md) `7-role-prompts-from-idea-to-done` | Still walking a senior AI through every step: tech lead, requirements, debugging, performance, frontend, backend, reviewer. |
| [Herdr: Astra coordinating Claude Code workers](references/herdr-astra-coordinates-workers.md) `herdr-astra-coordinates-workers` | Your Claude Code subscription, used from Codex: Astra runs up to 10 Opus workers through Herdr and hands them the heavy work. |
| [Herdr: one task across Claude and Codex panes](references/herdr-claude-and-codex-panes.md) `herdr-claude-and-codex-panes` | Relaying conclusions between windows by hand: the task split, a worktree and outcome per agent, one executes, one reviews. |
| [To-dos first in long reports: an AGENTS.md rule](references/to-dos-first-in-long-reports.md) `to-dos-first-in-long-reports` | What it needs from you is buried mid-report: one AGENTS.md section puts the to-dos, numbered, at the top of every report. |
| [Slow-computer audit when agents run](references/slow-computer-audit-for-agents.md) `slow-computer-audit-for-agents` | Many agents open and the Mac bogs down: a dry-run map of processes and startup items, cleaned only where you approve. |
- | [The job worth a dynamic workflow](references/job-worth-a-dynamic-workflow.md) `job-worth-a-dynamic-workflow` | Which job is worth many agents: repo-wide checks, migrations or fix loops, planned on one directory with at most 10 agents. |
+ | [The job worth a dynamic workflow in Claude Code](references/job-worth-a-dynamic-workflow.md) `job-worth-a-dynamic-workflow` | Which job is worth many agents: repo-wide checks, migrations or fix loops, planned on one directory with at most 10 agents. |
| [Bedtime report of tasks safe to run overnight](references/bedtime-report-of-safe-tasks.md) `bedtime-report-of-safe-tasks` | Unused quota overnight: an hour before bed, 3-5 reversible, verifiable tasks from today, prompts ready, nothing changed. |
| [Orca: one task split across CLI agents](references/orca-a-task-across-cli-agents.md) `orca-a-task-across-cli-agents` | Who finished what across several CLI agents: a goal each, read-only reviewers, worktrees for writers, one owner integrates. |
| [HANDOFF.md for the next agent](references/handoff-md-for-the-next-agent.md) `handoff-md-for-the-next-agent` | A task longer than one session: progress, decisions, files, checks and next steps kept current for the next agent. |
| [Decision page rule for long tasks](references/decision-page-for-long-tasks.md) `decision-page-for-long-tasks` | A summary saying all went well hides the agent's choices: one screen of the ones that change the result, those to confirm in red. |
| [Codex remote workflow from OpenAI's guide](references/codex-remote-workflow.md) `codex-remote-workflow` | Projects that keep moving while you're out: OpenAI's Remote guide applied, what runs alone and what you decide by phone. |
| [Scheduled-agents review by Anthropic's guide](references/scheduled-agents-review.md) `scheduled-agents-review` | 'The last 24 hours' in a scheduled task skips or repeats work: fixed windows, silent read failures and risky posting flagged. |
| [Overnight /goal for open issues and TODOs](references/overnight-goal-for-open-issues.md) `overnight-goal-for-open-issues` | Before bed: each issue and TODO taken as far as it can go without you, then one HTML board of what's done, stuck or your call. |
| [Goal wrapper and 5 prompts built on it](references/goal-wrapper-and-5-prompts.md) `goal-wrapper-and-5-prompts` | One preference typed in three places: a goal wrapper, plus prompts for components, parallel runs, review, states and corrections. |
+ | [One-way door rules for AGENTS.md: when to ask](references/one-way-door-rules-when-to-ask.md) `one-way-door-rules-when-to-ask` | Questions you'd only rubber-stamp: work you can undo done and shown after, a stop at anything you can't undo. |
+ | [Coordinator skill for Claude Code and Codex](references/coordinator-for-claude-and-codex.md) `coordinator-for-claude-and-codex` | Too much for one agent session: a coordinator that never codes runs Claude and Codex workers in Herdr and ships tested batches. |