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 agentmods add skills/tanstack/ai/pr-descriptionnpx skills add TanStack/ai --skill pr-descriptiongit clone --depth 1 https://github.com/TanStack/aiWhat 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 | $0.00072 | $0.02087 |
| Opus 5 | $0.00036 | $0.01043 |
| Sonnet 5 | $0.00014 | $0.00417 |
| Haiku 4.5 | $0.00007 | $0.00209 |
Grade A, and why
pr-description 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 yesterday.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-description
Write the GitHub PR title and body, then post them. Do not wait for approval.
Work from the diff, not from memory.
When to run
This skill is auto plus on demand.
Run it:
- When the user asks for a PR title or body, or types
/pr-description. - Immediately before
gh pr create. - Immediately after an agent
git pushon a branch that already has an open PR. Then rungh pr editwith a fresh title and body.
Do not run it on a human-only git push in another terminal. Do not add a git hook.
A later push must rewrite the GitHub text. Do not leave a stale description.
A fix PR must pass bugfix-pr first. If those gates fail, stop. Do not run gh pr create. Do not run gh pr edit.
Required skills for the title and body
simple-english and i-have-adhd are prerequisites. They apply to the PR title and body, not to the rest of the session.
Load both immediately before writing the title and body. Use the Skill tool if this harness has one. If it does not, Read:
.claude/skills/simple-english/SKILL.md.claude/skills/i-have-adhd/SKILL.md
Copies also live at .agents/skills/ (Codex) and .grok/skills/ (Grok). Keep those three files identical.
If either file is missing, stop. Do not post a weaker substitute.
When i-have-adhd is loaded from this skill, ignore its persistence section. Do not switch the rest of the session into ADHD mode.
Use pragmatic simple-english. Then shape the text with i-have-adhd: next action first in the lead, numbered steps for manual test, lists capped at 5.
Procedure
1. Ground in the repo
- Find the base branch (
main/master/develop). - Read
git log --oneline base...HEADandgit diff base...HEAD. - Read
.github/pull_request_template.mdif it exists (also check.github/PULL_REQUEST_TEMPLATE.mdand.github/PULL_REQUEST_TEMPLATE/). - Read about 15 recent PR titles in this repo (
gh pr list --limit 15 --state all --json title). Match that shape. Do not invent a new title style. - Collect linked issues from branch name, commit messages, and
Closes #/Fixes #text.
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.
- yesterday First seen · 200 lines · 72 tokens per session scan A f510590be362
pr-description is a skill published in the GitHub repository TanStack/ai (3,045 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,087 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
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
options
Present multiple design options as a vertical stack of anchored turns.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
workflow-authoring
Reference for writing a Workflow tool script (script API and gotchas, resume, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.