SessionStart
01Hook Claude Code
Runs when a session starts, executing auto-recall.sh via bash. From kevglynn/ai-dev-playbook.
3 2mo ago A
tokens not measured
PostToolUse
02Hook Claude Code
Runs after a tool call finishes for Bash tool calls, executing memory-capture.sh via bash. From kevglynn/ai-dev-playbook.
3 2mo ago A
tokens not measured
SubagentStop
03Hook Claude Code
Runs when a subagent finishes, executing subagent-wrapup.sh via bash. From kevglynn/ai-dev-playbook.
3 2mo ago A
tokens not measured
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, PostToolUse, SubagentStop).
3 2mo ago A
tokens not measured
Agent Cursor
Analyzes and proposes deeper, more mature usage of beads (bd) across the playbook. Use proactively when evaluating beads adoption patterns, workflow maturity, or proposing advanced beads features. Deeply familiar with both the ai-dev-playbook repo and the bd CLI.
3 2mo ago A 58 tokens
Agent Cursor
Designs better documentation, onboarding guides, scripts, and automation for the ai-dev-playbook. Use proactively when evaluating docs quality, onboarding friction, automation gaps, or proposing new scripts and guides. Deeply familiar with the entire repo.
3 2mo ago A 53 tokens
Agent Cursor
Measures the causal link between playbook rule changes and observed agent behavior shifts. Use proactively after rule edits to establish baselines, run before/after comparisons, analyze agent transcripts for adherence patterns, and determine which rules are landing vs being ignored. Deeply familiar with the…
3 2mo ago A 79 tokens
Agent Cursor
Audits and improves the 8 canonical agent rules (.mdc files) and sync/worktree scripts. Use proactively when evaluating rule quality, coverage gaps, consistency, or when proposing new rules. Deeply familiar with the ai-dev-playbook repo structure.
3 2mo ago A 56 tokens
Agent Cursor
Creative strategist for the ai-dev-playbook. Generates novel ideas to extend the playbook's value beyond incremental improvements. Use proactively when brainstorming new capabilities, exploring unconventional approaches, or thinking about what the playbook could become. Deeply familiar with the repo and the broader…
3 2mo ago A 64 tokens
Instructions file CodexOpenCode
AGENTS.md instructions for kevglynn/ai-dev-playbook, covering agents.md, about this repo, for bootstrapping target repos, one-command setup for a target project and verify setup.
3 2mo ago A 657 tokens
Instructions file
Claude Code instructions for kevglynn/ai-dev-playbook, covering claude.md, jawnt context rule, available jawnt mcp tools, when to use jawnt and when not to use jawnt.
3 2mo ago A 1,552 tokens
Cursor rule
Agents are not humans — do not estimate timelines, effort, or team size using human baselines.
3 2mo ago A 734 tokens
Cursor rule
How agents pick up, verify, and close beads — JIT verification, self-review against ACs, evidence policy, and bd remember knowledge capture.
3 2mo ago A 1,518 tokens
Cursor rule
Standards for creating and closing beads — every bead must be self-contained with ACs, and every close must include evidence.
3 2mo ago A 1,492 tokens
Cursor rule
Convention for marking deliberate simplifications with ceiling and upgrade trigger. Prevents "later means never" by requiring each deferral to name its limitation and the condition for revisiting.
3 2mo ago A 620 tokens
design-docs
16Cursor rule
When and how to create committed design specs for larger initiatives.
3 2mo ago A 441 tokens
Cursor rule
Multi-agent code review protocol — same-model multi-lens (autonomous) + cross-model (human-assisted) for structural changes.
3 2mo ago A 1,753 tokens
Cursor rule
Planner/Executor operating model — role definitions, workflow, scratchpad conventions, and beads task tracking.
3 2mo ago A 3,978 tokens
Cursor rule
Prevents file-edit conflicts between the parent agent and running subagents — do not touch files in a subagent's blast radius until it completes.
3 2mo ago A 817 tokens
Cursor rule
Lazy senior dev implementation mode — the decision ladder for minimal, correct code. Activate with 'use ponytail-playbook' or when implementing feature/task beads where code minimalism matters. Defers to pragmatic-tdd.mdc for test discipline.
3 2mo ago A 48 tokens
Cursor rule
Signal-first TDD — test discipline varies by bead type. Prevents zero-signal tests and over-testing.
3 2mo ago A 1,022 tokens
Cursor rule
Session start/close protocol — the first and last things an agent does in every session. Mandatory.
3 2mo ago A 333 tokens
Cursor rule
Git worktree isolation, shared beads DB, and worktree lifecycle for multi-branch development.
3 2mo ago A 919 tokens
Skill Claude CodeCodex
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when…
3 2mo ago A 76 tokens