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 paulbaranowski/wild-horses --skill wild-prgit clone --depth 1 https://github.com/paulbaranowski/wild-horsesWrote 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/paulbaranowski/wild-horses/wild-pr)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/wild-pr"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/wild-pr/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/paulbaranowski/wild-horses/wild-pr"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/wild-pr.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 | $0.00069 | $0.02775 |
| Opus 5 | $0.00034 | $0.01388 |
| Sonnet 5 | $0.00014 | $0.00555 |
| Haiku 4.5 | $0.00007 | $0.00278 |
Grade A, and why
wild-pr 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 11d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wild-pr — create PR, then babysit ×3
Open a PR for the current branch, write its description with summary-writer, then tend it with babysit up to three times (stop early if a pass exits clean).
Dependencies (must be available this session):
summary-writer(this plugin) — description + titlebabysit(this plugin) — CI + review tending
If either skill is missing, stop and tell the user what to install. Do not invent a substitute description format or a hand-rolled babysit loop.
Arguments: $ARGUMENTS — optional base branch name, or extra flags to pass through to gh pr create (e.g. --draft). Only pass values that are valid gh pr create flags or a base branch name — do not dump free-form prose into the create command.
The PR link rule
Two moments make a PR URL known. /wild-pr creates the PR, or preflight finds one that already exists. From then on, end every message with the link on its own last line:
PR: https://github.com/<owner>/<repo>/pull/<n>
This holds on every exit path. Those are: clean, three passes spent, hard stuck, aborted mid-run, and a preflight PR that already existed. Print the full URL. A bare number does not satisfy this rule, so PR #340 created is a failure.
The rule outlives the phase that captured the URL. Placement differs by writer: your own messages end with the link, and a babysit report leads with it. Restate the line yourself after each pass, so your message still ends with it.
Composing other skills
For each dependency skill or command:
- Locate its installed
SKILL.mdorcommands/*.md(plugin cache, marketplace checkout, or session skill list). - Read that file with the Read tool — do not rely on memory or a paraphrase.
- Execute it fully, then return here to the next phase.
Don't paraphrase either dependency from memory. Don't skip the Read step even if you have used it before in this conversation.
When invoking babysit, treat the captured PR URL (or number) as the command's argument text — as if the user had run /wild-pr:babysit <url>. That feeds its Setup parser so it targets the right PR.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 208 lines · 69 tokens per session scan A 6263ed6a30a5
wild-pr is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 23d ago), licensed MIT. It adds 69 tokens to every session and 2,775 once invoked, about $0.0003 per session on Opus 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
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
github-sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
github-notification-triage
Triage GitHub notifications and issue/PR queues.