Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dmae97/omk --skill ponytail-debtgit clone --depth 1 https://github.com/dmae97/omkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dmae97/omk/ponytail-debt)<a href="https://agentmods.dev/skills/dmae97/omk/ponytail-debt"><img src="https://agentmods.dev/badge/skills/dmae97/omk/ponytail-debt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dmae97/omk/ponytail-debt"><img src="https://agentmods.dev/badge/skills/dmae97/omk/ponytail-debt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.01015 |
| Opus 5.5 | $0.00040 | $0.00406 |
| Sonnet 5.5 | $0.00020 | $0.00203 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
ponytail-debt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
OMK Vendoring Notice
This skill is vendored from the upstream Ponytail
project (npm: @dietrichgebert/ponytail) as a pure markdown OMK skill, copied unmodified in
substance from skills/ponytail-debt/SKILL.md at pinned commit
40e50d9
(full SHA 40e50d9e03242aa5dd53ac771950f9127362b25f).
- License: MIT. Copyright (c) 2026 DietrichGebert. Full text:
../ponytail/LICENSE(this repo's vendored copy, kept alongside the primaryponytailskill) and the upstreamLICENSEfile at the pinned commit. - Scope: only the six
skills/*/SKILL.mdfiles were vendored. Upstream's Node/Python extension code (pi-extension/,hooks/*.js,ponytail-mcp/), the Hermes Agent plugin (__init__.py,plugin.yaml), command/hook manifests, and marketplace/CI tooling are not included in OMK. Nothing in this skill executes code; it is inert markdown loaded into the system prompt. - Invocation in OMK: use
/skill:ponytail-debtor!skill:ponytail-debt(shorthand!ponytail-debtalso works when unambiguous), perpackages/coding-agent/docs/skills.md. The bare/ponytail-debtslash form referenced above describes the upstream multi-host package's own command surface (Claude Code, Codex, OpenCode, etc.) and is not an OMK command. - Updates: this is a static vendored copy, not a live package install. To pick up upstream changes, re-vendor against a newer pinned commit; there is no auto-update mechanism here.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 77 lines · 99 tokens per session scan A 106167b4adcc
ponytail-debt is a skill published in the GitHub repository dmae97/omk (149 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,015 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pi-review-gated-delivery
Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.
setup
Install and configure SyncPoint — set up a multi-agent coordination project from scratch. Use when the user asks to set up SyncPoint, initialize agent coordination, or create a multi-agent project.
agent-loop
Run the SyncPoint orchestration loop — boot a task, create checkpoints, hand off work between agents. Use when coordinating multiple AI agents on the same task, or when resuming from a previous checkpoint.
handoff
Hand off work between AI agents in SyncPoint — checkpoint progress, transfer task ownership, resume from snapshot. Use when an agent finishes work and needs to pass context to another agent.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.