mcpField
P
ponytail-help

ponytail-help

github.com/dietrichgebertAgent workflows179.1k45.0k installsUpdated 1w ago
Repository

About ponytail-help

ponytail-help is a reference skill for users of Ponytail in coding-agent environments. It explains the available modes, companion skills, activation and configuration, and host-specific controls.

Key features

  1. 01Mode and skill reference
  2. 02Activation and deactivation commands
  3. 03Default-mode configuration
  4. 04Claude Code band controls
  5. 05Plugin update guidance

Use cases

  1. 01Checking what each Ponytail mode does
  2. 02Finding the command for a companion skill
  3. 03Changing the default mode
  4. 04Reviewing Claude Code display and update controls

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/dietrichgebert/ponytail --skill ponytail-help

After installing, type/ponytail-helpin Claude Code to confirm it loaded.

Details

From the project README

Ponytail Help

Display this reference card when invoked. One-shot, do NOT change mode, write flag files, or persist anything.

Levels

LevelTriggerWhat change
Lite/ponytail liteBuild what was asked, name the smaller option in one line.
Full/ponytailThe smallest complete change, a check where the logic needs one, and a reply that names what was skipped and any risk. Default.
Ultra/ponytail ultraAlso questions the request and pushes back before building.

Level sticks until changed or session end.

Skills

SkillTriggerWhat it does
ponytail/ponytailLazy mode itself: least new code, clear replies that name skipped work and risks.
ponytail-review/ponytail-reviewQuality review of a diff: bugs, security, load, missing tests, speed, what to cut. Each finding says what goes wrong and how to fix it.
ponytail-audit/ponytail-auditThe same quality review for the whole repo, ranked.
ponytail-debt/ponytail-debtHarvest shortcut: comments into a tracked ledger.
ponytail-gain/ponytail-gainMeasured-impact scoreboard: less code, less cost, more speed.
ponytail-help/ponytail-helpThis card.

In Codex CLI and the IDE extension, invoke skills with $ponytail:ponytail, $ponytail:ponytail-review, or $ponytail:ponytail-help. Claude Code and OpenCode use the slash-command forms above (OpenCode ships all six as slash commands).

Deactivate

Say "stop ponytail" or "normal mode". Resume anytime with /ponytail. /ponytail off also works.

Band (Claude Code)

/ponytail band hides the band above the prompt, the same command brings it back. /ponytail band on and /ponytail band off set it directly. The level stays. /ponytail band import adds your past Claude Code sessions (cost, agent time, tokens) to the board.

Configure Default Mode

Default mode = full, auto-active every session. Change it:

Environment variable (highest priority):

export PONYTAIL_DEFAULT_MODE=ultra

Config file (~/.config/ponytail/config.json, Windows: %APPDATA%\ponytail\config.json):

{ "defaultMode": "lite" }

Set "off" to disable auto-activation on session start, activate manually with /ponytail when wanted.

Resolution: env var > config file > full.

Update

Enable auto-update once: open /plugin, go to Marketplaces, pick ponytail, Enable auto-update. Claude Code then pulls new versions at startup (run /reload-plugins when it prompts). Manual refresh: /plugin marketplace update ponytail then /reload-plugins.

If /plugin is not recognized, your Claude Code is out of date. Update it (npm install -g @anthropic-ai/claude-code@latest, or brew upgrade claude-code) and restart. Other hosts use their own update flow.

More

Full docs + examples: https://github.com/DietrichGebert/ponytail

Comments

Markdown supported