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/summary-writer)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/summary-writer"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/summary-writer/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/summary-writer"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/summary-writer.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 | $0.00080 | $0.09318 |
| Opus 5 | $0.00040 | $0.04659 |
| Sonnet 5 | $0.00016 | $0.01864 |
| Haiku 4.5 | $0.00008 | $0.00932 |
Grade A, and why
summary-writer 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 — 772 lines — stays where its author put it; the contents beside it link to each section on GitHub.
summary-writer
Write PR descriptions that lead with what changed structurally, not a catalog of edits. The reviewer should understand what changed and why before opening the diff. Per-file detail lives in the commits and in the code. The description gives the reader the mental model that the diff assumes.
Core principle: one idea per PR, stated once, up front. Every PR worth a description has one main structural idea. Find it, then state it in one sentence. Let every other sentence follow from it. If you cannot state the one idea, the PR is either trivial or too big. A trivial PR gets a short description. A PR that is too big should be split.
State the idea directly. Never announce it. The first sentence of the architecture section makes a claim about the system. It does not announce that a claim is coming. Write "Event extraction no longer saves events". Do not write "The core move is...", "The main change here is...", or "At a high level, this PR...". Start talking about the change. Delete the sentence that says you are about to.
Describe the net diff against the base, not the branch's history. The
reviewer sees <base>...HEAD on GitHub. That one collapsed change is the only
thing the description exists to explain. The branch may contain approaches you
tried and reverted, commits that replaced earlier commits, and pivots you made
partway through. None of that appears in the diff, so none of it appears in the
description. The state before this PR is main. The state after is HEAD. Nothing
in between belongs.
Calling this skill
Another skill invoking summary-writer needs only this section. Never restate
these rules in the caller. Point at this section instead.
Supply: the branch or PR to describe, and the source issue or plan URL. Also every ambiguous call with the alternatives you considered, and any review dismissals. The last two belong in Decision review. That is this skill's name for the section a caller may know as "Decisions".
Receive: a title and a body. This skill re-derives the title on every run, so an existing title is input, never a default. Use both.
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 · 772 lines · 80 tokens per session scan A 6a939b54289f
summary-writer is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 23d ago), licensed MIT. It adds 80 tokens to every session and 9,318 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…