Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add paulbaranowski/wild-horses/plugin install wild-prWrote 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/review)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/review"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/review/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/review"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/review.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 | $0.00074 | $0.04692 |
| Opus 5 | $0.00037 | $0.02346 |
| Sonnet 5 | $0.00015 | $0.00938 |
| Haiku 4.5 | $0.00007 | $0.00469 |
Grade A, and why
review 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review
Review a diff against one rubric and filter to the few findings worth raising. Gate with the user, then optionally post as anchored PR comments. --report replaces the gates with a findings report for an agent caller. Two engines share everything except how the rubric is applied:
- low - one reviewer subagent, single pass. Default.
- high - parallel reviewer subagents, one debate round, moderator filter. For large or high-stakes diffs.
Invocation
/wild-pr:review- review the current branch. This resolves the branch's open PR if any, and otherwise diffs against the default branch./wild-pr:review <pr-number-or-url>- review that PR without checking it out; forces reviewer mode. Accepts a bare number (current repo) or full GitHub URL (identifies owner/repo).--effort low|high- pick the engine explicitly. Phrases also select: "quick"/"fast" → low; "deep"/"thorough"/"multi-perspective" → high.--report- non-interactive: stop after Synthesize and return the findings to the caller. No user gates, no posting, no implementing. For agent callers.
Effort auto-select (no flag, no phrase): high when the diff exceeds 20 changed files or 600 changed lines, else low. Before reviewing, print one line: Effort: <low|high> (<N> files, <M> lines; override with --effort <other>). The line lets the user interrupt.
Calling this skill
Another skill invoking review needs only this section. Never restate these rules in the caller. Point at this section instead.
Commit first. This skill reviews the committed diff against the base branch, never the working tree. An uncommitted change reads to it as an empty diff, and the review silently no-ops.
Supply: the branch or PR, and nothing else. This skill derives its own spec context from the commit messages and the PR body. Never feed it your reasoning or your conversation, because the value is in independent judgment.
Use --report when the caller is an agent. It stops after Synthesize and returns the findings. It runs no user gates, posts nothing, and implements nothing. Every interactive checkpoint resolves to its safe default instead of prompting.
What ships with it
4 files 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 · 287 lines · 74 tokens per session scan A 4f2440a43ffd
review is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 4,692 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…