A workflow that drafts a pull request description and one issue for a completed optimization campaign. A pull request is a proposed code change for review; an issue records follow-up work for a project.

Use it to create reviewable Markdown files from campaign reports, benchmarks, traces, and candidate records for the user to inspect and post.

It helps maintainers quickly understand what was wrong, what changed, and what costs or risks the change carries, without overstating the evidence.

publish-pr — Skill for Claude Code by wenhaochai/claude-plugins

Install

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.

Any agent

npx skills add wenhaochai/claude-plugins --skill publish-pr

Clone the repo

git clone --depth 1 https://github.com/wenhaochai/claude-plugins

Made for: Claude Code.

Or install who-ate-my-flops, the plugin that ships this one along with the rest of its 9 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/publish-pr/github.svg)](https://agentmods.dev/skills/wenhaochai/claude-plugins/publish-pr)

Your own site

<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/publish-pr"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/publish-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/publish-pr"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/publish-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,258 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00113	$0.02258
Opus 5.5	$0.00045	$0.00903
Sonnet 5.5	$0.00023	$0.00452
Haiku 4.5	$0.00011	$0.00226

Measured 14d ago against content hash b834c5029456, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publish-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 14d 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.

who-ate-my-flops/skills/publish-pr/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft the PR description and the issue

In: a campaign that clean-up has delivered (delivery branch, benchmark.csv, records/candidates.jsonl, commits/<sha>/{report.md,trace/}, latest-report.md), and the target repo checkout. Out: proposed-pr-description.md and proposed-issue.md next to latest-report.md. The user uploads traces, pushes, opens the PR and files the issue.

The reader is a maintainer who has never heard of you, the campaign or its tools. They open the PR wanting three answers, in this order: what was wrong, what this PR changes, and what it costs or risks. Everything else is evidence, and evidence goes lower down or into a collapsed block. The filled example is template/pr-description.example.md (https://github.com/modelscope/FunASR/pull/3705).

1. Decide what the PR may claim

Before writing, sort every shipped change:

Install or setting a user can apply alone (a pip package the code already falls back to, an env var, a launcher flag, a config value): not the PR's contribution. Apply it to both arms of the measurement and name it in Details, with the rest of the measurement setup. The speedup the PR claims is measured on top of it.
A default the repo should ship for its users (users of the recipe cannot be expected to know the setting): this is a contribution. Keep it as code, behind an explicit option that is off for every other caller, and turn it on in the recipe.
Source changes: the contribution.
Removed code: before claiming a removal is safe, git blame it and read the PR that added it. Code that looks useless often guards a case the benchmark does not exercise (mixed data, other devices, other launchers). If you cannot show the case is covered, do not ship the removal.

Every number comes from benchmark.csv, records/candidates.jsonl, commits/<sha>/report.md, latest-report.md or a re-verification run. Nothing predicted, nothing remembered, nothing carried over from an earlier baseline without saying so.

Read the full file on GitHub · 124 lines

Changes

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.

14d ago Changed · +23 tokens per session b834c5029456
17d ago First seen · 124 lines · 90 tokens per session scan A 9277d5b194e4

Subscribe to this mod's changes

publish-pr is a skill published in the GitHub repository wenhaochai/claude-plugins (17 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 2,258 once invoked, about $0.0005 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 2026-10-01.

Code review Git and workflow

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Yeachan-Heo/oh-my-claudecode · 47 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens