Borrowing it
Nothing to install: this file belongs to hachej/boring-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hachej/boring-ui/main/.agents/skills/present-pr/SKILL.mdgit clone --depth 1 https://github.com/hachej/boring-uiWrote 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/hachej/boring-ui/present-pr)<a href="https://agentmods.dev/skills/hachej/boring-ui/present-pr"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/present-pr.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.03337 |
| Opus 5 | $0.00034 | $0.01669 |
| Sonnet 5 | $0.00014 | $0.00667 |
| Haiku 4.5 | $0.00007 | $0.00334 |
Grade A, and why
present-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 3d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Present PR
This is the standard final step of every implementation PR: before requesting owner validation, generate the presentation (composed context visuals + summary + sankey + importance-ordered diffs) and publish/hand the artifact to the owner.
The review flow it encodes, in the owner's own order:
- What review already happened — was this deep-audited? thermo-reviewed? what failed and did it get fixed? Answerable yes/no without reading a single comment thread.
- What areas/packages are touched —
packages/vsapps/vs the rest. - Per-package scope check — a PR reaching into a package it has no business in is visible at a glance, with that package's ±line counts on the node.
- Why is each file in this PR at all — one line per file or group, readable by skimming headers without opening a single diff.
- Most important diffs first — not alphabetical, not whatever GitHub shows first.
A GitHub PR page answers none of these: it opens on a path-sorted file list with lockfiles and snapshots competing with the one file that decides the review.
When to use
- Any implementation PR that is CI-green and audited and needs a merge decision.
- A change spanning several packages, where "which seam does this touch?" comes first.
Do not use it as a substitute for the review itself. Present only what you have already reviewed, and state the open questions.
Steps
-
Understand the seam. Read the production files first and
../show-me/SKILL.md. Identify the flow the PR changes—entry point → policy/decision → effect—and compose the views that make that seam easiest to review. -
Write the context sidecar — one markdown file, per PR, at
<scratchpad>/pr-<n>-context.md:# PR <n> context ```text submitForm createSession + expandSkillMention launchAgent navigateToSession ``` ```ts type SubmitResult = + | { status: 'expanded'; skill: string } | { status: 'started'; sessionId: string } ```
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.
- 3d ago First seen · 255 lines · 68 tokens per session scan A 03093b1c6f71
present-pr is a skill published in the GitHub repository hachej/boring-ui (46 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 3,337 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…