A cross-tool field guide to how I build with AI agents, with practical workflows and portable skills from research to maintenance.
This repository also configures its own agents. See what the-rookery tells them →
Skill Claude CodeCodex
Use when a reviewed pull request is about to be merged, including digest this PR before I merge, should I merge this, or merge this PR. Briefs merge, debug, or do not merge plus numbered live options and waits for a numbered reply. Option 1 is Proceed to merge. A bare merge request still runs this review and still…
Skill Claude CodeCodex
Use when branch work looks complete and needs a readiness decision before another workflow opens a pull request, or when asked to assess a specific head for PR readiness. Gathers the working surface and checks, then briefs a recommendation plus numbered live options and waits for a numbered reply. Option 1 is Approve.…
Skill Claude CodeCodex
Use when creating, updating, or migrating a skill, when editing a skill's SKILL.md, evals, graders, or trigger queries, or when finding problems in its description, triggers, structure, portability, or evidence. Produces prioritized findings or a portable, installable skill package. Explanation-only requests stay with…
Skill Claude CodeCodex
Use when the requested outcome is reading, drafting, creating, or surgically updating GitHub or Linear issue records; changing their native parent, sub-issue, or blocker relationships and assessing readiness; checking completion against Verification evidence; or reversibly closing or canceling an issue. Do not use for…
Skill Claude CodeCodex
Use when the user asks to capture a relationship interaction, prepare for one person, clean up or reconstruct Person notes, review overdue relationships, discover who could help with current work, when another workflow finds a possible relationship effect, or when the user later confirms or revises a required catch-up…
Skill Claude CodeCodex
Use when the user wants to complete a daily journal or wind down, requests a daily chief-of-staff review, requests a weekly or quarterly review, later revisits, resumes, approves, edits, defers, skips, or otherwise decides visible chief-of-staff actions, or another workflow requests current cross-source chief-of-staff…
Skill Claude CodeCodex
Use when running or interpreting a scheduled or manual repository-gardening pass for one repository, including first-use setup of .agents/repo-gardener.yaml and its gardening tracker. Do not use for merging, releasing, deploying, creating follow-up issues, contacting customers, or performing an already-selected…
Skill Claude CodeCodex
Use when the user asks to review, process, import, catch up on, or check for newly completed meetings from a configured meeting source, including Granola; when a scheduled post-meeting review invokes it; or when the user later revisits, resumes, approves, edits, defers, skips, or otherwise decides visible…
Skill Claude CodeCodex
Use only for requests whose deliverable is a full research briefing, a STORM-style investigation, or an evidence review across multiple independent perspectives. The work compares competing evidence, maps contradictions and blind spots, and supports decisions, investments, negotiations, long-form writing…
Skill Claude CodeCodex
Use when the user asks to simplify, right-size, identify overengineering, compare with a stated smaller alternative, choose the smallest viable approach, check for simplicity as well, or test whether reuse removes the need for change on a named architecture, design, area, plan, technical choice, or code-level…
Skill Claude CodeCodex
Use only when the user explicitly asks to route a work kickoff to its first workflow owner or decide whether a proven in-flight owner should continue.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: