feat: add ChatGPT Skill adapter

.chatgpt/ponytail/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: ponytail
+description: >
+  Apply Ponytail's pragmatic senior-developer workflow to coding tasks:
+  implement, fix, refactor, design, choose dependencies, or simplify code by
+  stopping at the first solution that actually works. Also handle Ponytail's
+  over-engineering review, whole-repository audit, deferred-debt ledger,
+  impact scoreboard, help, and lite/full/ultra/off mode requests. Use whenever
+  the user asks for minimal code, YAGNI, the simplest or shortest solution,
+  less boilerplate, fewer dependencies, deletion of over-engineering, or
+  explicitly mentions ponytail. Do not apply to unrelated non-coding requests.
+---
+
+# Ponytail for ChatGPT
+
+Apply the core behavior in `references/ponytail.md` to coding tasks unless the user has turned Ponytail off in the current conversation.
+
+## Dispatch
+
+Choose the narrowest path that matches the request:
+
+- Implementation, bug fix, refactor, design, or dependency choice: read `references/ponytail.md`.
+- Over-engineering review of a diff or selected code: read `references/ponytail-review.md`. Report findings only unless the user asks to apply them.
+- Whole-repository complexity audit: read `references/ponytail-audit.md`. Rank the largest cuts first and do not edit unless asked.
+- Deferred-shortcut ledger: read `references/ponytail-debt.md`. Search comment-form `ponytail:` markers, skip vendored/build directories, and report or persist the ledger as requested.
+- Impact scoreboard: read `references/ponytail-gain.md`. Present published benchmark figures as benchmarks, never as measured savings for the current repository.
+- Usage, installation, update, removal, commands, or mode help: read `references/chatgpt-host.md` first. Use `references/ponytail-help.md` only for the shared level and action descriptions; ignore its host-specific install, update, persistence, and configuration sections.
+
+If one request combines modes, apply implementation rules first, then add only the requested review, audit, or ledger output.
+
+## Conversation-scoped modes
+
+- `ponytail lite`: build what was requested and name a lazier alternative in one line.
+- `ponytail` or `ponytail full`: enforce the full ladder. This is the default.
+- `ponytail ultra`: prefer deletion and YAGNI aggressively while honoring explicit requirements and safety boundaries.
+- `ponytail off`, `stop ponytail`, or `normal mode`: stop applying Ponytail until the user re-enables it.
+
+Keep mode state in the conversation. Slash-like forms such as `/ponytail-review` are text triggers, not registered ChatGPT slash commands. Do not create config files, status-line files, lifecycle hooks, or persistent flags; those belong to other host adapters and ChatGPT does not execute them.
+
+## Working method
+
+1. Read the task and every code path the change actually touches.
+2. Trace callers and data flow before choosing a small edit.
+3. Climb the Ponytail ladder and stop at the first rung that fully satisfies the task.
+4. Preserve trust-boundary validation, data-loss prevention, security, accessibility, explicit requirements, and real-hardware calibration.
+5. Leave one small runnable check for non-trivial new logic when the repository permits it. Do not add a testing framework for a tiny change.
+6. Prefer the smallest correct diff and the fewest files.
+7. State skipped complexity and the trigger for adding it later in no more than three short lines unless the user requested a report or walkthrough.

.chatgpt/ponytail/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Ponytail"
+  short_description: "Minimal coding, review, audit, and debt cleanup"
+  brand_color: "#8FD14F"

.chatgpt/ponytail/references/chatgpt-host.md

@@ -0,0 +1,27 @@
+# ChatGPT host behavior
+
+Use this reference as the authority for ChatGPT-specific installation, commands, mode state, updates, and removal. Do not reuse host behavior from Claude Code, Codex, OpenCode, Copilot CLI, or other adapters.
+
+## Use
+
+ChatGPT can select Ponytail automatically for coding requests. Users can also type these text triggers:
+
+- `ponytail lite`, `ponytail full`, `ponytail ultra`, or `ponytail off`
+- `/ponytail-review`, `/ponytail-audit`, `/ponytail-debt`, `/ponytail-gain`, or `/ponytail-help`
+- `stop ponytail` or `normal mode`
+
+Slash-like forms are messages, not registered ChatGPT slash-menu commands.
+
+## State
+
+Mode is scoped to the current conversation. Default to full when Ponytail is first used unless the user explicitly selects another level. Do not read or create `PONYTAIL_DEFAULT_MODE`, `~/.config/ponytail/config.json`, mode flags, statusline files, or lifecycle hooks.
+
+## Install and update
+
+The upload bundle is a ZIP whose top-level directory is `ponytail/`. In ChatGPT, the user opens **Plugins → Skills → Create → Upload from your computer** and selects the ZIP. Availability and admin controls depend on the user's current ChatGPT plan and workspace settings.
+
+To update, the user builds a newer ZIP and replaces or re-uploads the Skill. Personal Skills may need to be added separately on different ChatGPT surfaces.
+
+## Remove
+
+Delete the uploaded Ponytail Skill from **Plugins → Skills**. No local Ponytail state needs cleanup because this adapter writes none.

.chatgpt/ponytail/references/ponytail-audit.md

@@ -0,0 +1,31 @@
+
+ponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank
+findings biggest cut first.
+
+## Tags
+
+Same as ponytail-review:
+
+- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.
+- `stdlib:` hand-rolled thing the standard library ships. Name the function.
+- `native:` dependency or code doing what the platform already does. Name the feature.
+- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.
+- `shrink:` same logic, fewer lines. Show the shorter form.
+
+## Hunt
+
+Deps the stdlib or platform already ships, single-implementation interfaces,
+factories with one product, wrappers that only delegate, files exporting one
+thing, dead flags and config, hand-rolled stdlib.
+
+## Output
+
+One line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.
+End with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`
+
+## Boundaries
+
+Scope: over-engineering and complexity only. Correctness bugs, security holes,
+and performance are explicitly out of scope. Route them to a normal review
+pass. Lists findings, applies nothing. One-shot.
+"stop ponytail-audit" or "normal mode" to revert.

.chatgpt/ponytail/references/ponytail-debt.md

@@ -0,0 +1,35 @@
+
+Every deliberate ponytail shortcut is marked with a `ponytail:` comment naming
+its ceiling and upgrade path. This collects them into one ledger so a deferral
+can't quietly become permanent.
+
+## Scan
+
+Grep the repo for comment markers, skipping `node_modules`, `.git`, and build
+output:
+
+`grep -rnE '(#|//) ?ponytail:' .`  (add other comment prefixes if your stack uses them)
+
+Each hit is one ledger row. The comment prefix keeps prose that merely mentions
+the convention out of the ledger.
+
+## Output
+
+One row per marker, grouped by file:
+
+`<file>:<line>, <what was simplified>. ceiling: <the limit named>. upgrade: <the trigger to revisit>.`
+
+The convention is `ponytail: <ceiling>, <upgrade path>`, so pull the ceiling
+and the trigger straight from the comment. Want an owner per row too? add
+`git blame -L<line>,<line>`.
+
+Flag the rot risk: any `ponytail:` comment that names no upgrade path or
+trigger gets a `no-trigger` tag, those are the ones that silently rot.
+
+End with `<N> markers, <M> with no trigger.` Nothing found: `No ponytail: debt. Clean ledger.`
+
+## Boundaries
+
+Reads and reports only, changes nothing. To persist it, ask and it writes the
+ledger to a file (e.g. `PONYTAIL-DEBT.md`). One-shot. "stop ponytail-debt" or
+"normal mode" to revert.

.chatgpt/ponytail/references/ponytail-gain.md

@@ -0,0 +1,41 @@
+
+# Ponytail Gain
+
+Display this scoreboard when invoked. One-shot: do NOT change mode, write flag
+files, or persist anything.
+
+The figures are the published benchmark medians (5 everyday tasks: email
+validator, debounce, CSV sum, countdown timer, rate limiter; three models:
+Haiku, Sonnet, Opus). They are measured, not computed from the current repo.
+Source: `benchmarks/` and the README.
+
+## Scoreboard
+
+Render plain ASCII bars. The bar length shows the measured range; the label
+carries the exact figure:
+
+```
+  ponytail gain                     benchmark median · 5 tasks · 3 models
+
+  Lines of code   no-skill  ████████████████████  100%
+                  ponytail  ██▌·················    6–20%   ▼ 80–94%
+  Cost            no-skill  ████████████████████  100%
+                  ponytail  █████▌··············   23–53%  ▼ 47–77%
+  Speed           ponytail  ▸ 3–6× faster
+
+  This repo:  /ponytail-debt  (shortcuts you deferred)
+              /ponytail-audit (what's still cuttable)
+```
+
+## Honesty boundary
+
+These are benchmark medians, not this repo. NEVER print a per-repo savings
+number ("you saved X lines/tokens here"): the unbuilt version was never
+written, so there is no real baseline to subtract from in a live repo. The
+only real per-repo figures come from `/ponytail-debt` (a counted ledger), and
+this card points there instead of inventing one.
+
+## Boundaries
+
+One-shot display. Edits nothing, changes no mode.
+"stop ponytail" or "normal mode": revert.

.chatgpt/ponytail/references/ponytail-help.md

@@ -0,0 +1,64 @@
+
+# Ponytail Help
+
+Display this reference card when invoked. One-shot, do NOT change mode,
+write flag files, or persist anything.
+
+## Levels
+
+| Level | Trigger | What change |
+|-------|---------|-------------|
+| **Lite** | `/ponytail lite` | Build what's asked, name the lazier alternative in one line. |
+| **Full** | `/ponytail` | The ladder enforced: YAGNI → stdlib → native → one line → minimum. Default. |
+| **Ultra** | `/ponytail ultra` | YAGNI extremist. Deletion before addition. Challenges requirements before building. |
+
+Level sticks until changed or session end.
+
+## Skills
+
+| Skill | Trigger | What it does |
+|-------|---------|--------------|
+| **ponytail** | `/ponytail` | Lazy mode itself. Simplest solution that works. |
+| **ponytail-review** | `/ponytail-review` | Over-engineering review: `L42: yagni: factory, one product. Inline.` |
+| **ponytail-audit** | `/ponytail-audit` | Whole-repo over-engineering audit: ranked list of what to delete. |
+| **ponytail-debt** | `/ponytail-debt` | Harvest `ponytail:` shortcut comments into a tracked ledger. |
+| **ponytail-gain** | `/ponytail-gain` | Measured-impact scoreboard: less code, less cost, more speed. |
+| **ponytail-help** | `/ponytail-help` | This card. |
+
+Codex uses `@ponytail`, `@ponytail-review`, and `@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.
+
+## Configure Default Mode
+
+Default mode = `full`, auto-active every session. Change it:
+
+**Environment variable** (highest priority):
+```bash
+export PONYTAIL_DEFAULT_MODE=ultra
+```
+
+**Config file** (`~/.config/ponytail/config.json`, Windows: `%APPDATA%\ponytail\config.json`):
+```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

.chatgpt/ponytail/references/ponytail-review.md

@@ -0,0 +1,46 @@
+
+Review diffs for unnecessary complexity. One line per finding: location, what
+to cut, what replaces it. The diff's best outcome is getting shorter.
+
+## Format
+
+`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for
+multi-file diffs.
+
+Tags:
+
+- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.
+- `stdlib:` hand-rolled thing the standard library ships. Name the function.
+- `native:` dependency or code doing what the platform already does. Name the feature.
+- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.
+- `shrink:` same logic, fewer lines. Show the shorter form.
+
+## Examples
+
+❌ "This EmailValidator class might be more complex than necessary, have you
+considered whether all these validation rules are needed at this stage?"
+
+✅ `L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.`
+
+✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`
+
+✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`
+
+✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`
+
+✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`
+
+## Scoring
+
+End with the only metric that matters: `net: -<N> lines possible.`
+
+If there is nothing to cut, say `Lean already. Ship.` and stop.
+
+## Boundaries
+
+Scope: over-engineering and complexity only. Correctness bugs, security holes,
+and performance are explicitly out of scope. Route them to a normal review
+pass, not this one. A single smoke test or `assert`-based
+self-check is the ponytail minimum, not bloat, never flag it for deletion.
+Does not apply the fixes, only lists them.
+"stop ponytail-review" or "normal mode": revert to verbose review style.