Cursor rule Cursor
Agents are not humans — do not estimate timelines, effort, or team size using human baselines.
not rated 4
+1 3mo ago A 734 tokens
Cursor rule Cursor
How agents pick up, verify, and close beads — JIT verification, self-review against ACs, evidence policy, and bd remember knowledge capture.
not rated 4
+1 3mo ago A 1,518 tokens
Cursor rule Cursor
Standards for creating and closing beads — every bead must be self-contained with ACs, and every close must include evidence.
not rated 4
+1 3mo ago A 1,492 tokens
Cursor rule Cursor
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.
not rated 4
+1 3mo ago A 620 tokens
design-docs
05Cursor rule Cursor
When and how to create committed design specs for larger initiatives.
not rated 4
+1 3mo ago A 441 tokens
Cursor rule Cursor
Multi-agent code review protocol — same-model multi-lens (autonomous) + cross-model (human-assisted) for structural changes.
not rated 4
+1 3mo ago A 1,753 tokens
Cursor rule Cursor
Planner/Executor operating model — role definitions, workflow, scratchpad conventions, and beads task tracking.
not rated 4
+1 3mo ago A 3,978 tokens
Cursor rule Cursor
Prevents file-edit conflicts between the parent agent and running subagents — do not touch files in a subagent's blast radius until it completes.
not rated 4
+1 3mo ago A 817 tokens
Cursor rule Cursor
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.
not rated 4
+1 3mo ago A 48 tokens
Cursor rule Cursor
Signal-first TDD — test discipline varies by bead type. Prevents zero-signal tests and over-testing.
not rated 4
+1 3mo ago A 1,022 tokens
Cursor rule Cursor
Session start/close protocol — the first and last things an agent does in every session. Mandatory.
not rated 4
+1 3mo ago A 333 tokens
Cursor rule Cursor
Git worktree isolation, shared beads DB, and worktree lifecycle for multi-branch development.
not rated 4
+1 3mo 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…
not rated 4
+1 3mo ago A 76 tokens
Skill Claude CodeCodex
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find…
not rated 4
+1 3mo ago A 105 tokens
Skill Claude CodeCodex
Harvest every defer: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did we defer", "list the shortcuts", "debt ledger", or "what did we mark to do later".…
not rated 4
+1 3mo ago A 92 tokens
Skill Claude CodeCodex
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
not rated 4
+1 3mo ago A 83 tokens
Skill Claude CodeCodex
Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
not rated 4
+1 3mo ago A 56 tokens
Skill Claude CodeCodex
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this…
not rated 4
+1 3mo ago A 100 tokens
Skill Claude CodeCodex
Structured approach to diagnosing and fixing bugs. Use when a bug is reported, a test fails unexpectedly, behavior doesn't match expectations, or when "something is wrong" but the cause isn't clear. Triggers on "debug this", "why is this broken", "this doesn't work", "investigate this failure", unexpected test…
not rated 4
+1 3mo ago A 79 tokens
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: