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 skills add fabis94/universal-ai-config --skill pr-descriptiongit clone --depth 1 https://github.com/fabis94/universal-ai-configWrote 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/fabis94/universal-ai-config/pr-description)<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/pr-description"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/pr-description/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/fabis94/universal-ai-config/pr-description"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/pr-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01744 |
| Opus 5 | $0.00024 | $0.00872 |
| Sonnet 5 | $0.00010 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00174 |
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 9d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a Pull Request Description
1. Pick the scope
First check the current branch: git rev-parse --abbrev-ref HEAD. Compare against the detected base (see step 2 — note that base detection includes a stacked-branch check that may prompt the user).
- On a feature branch (HEAD != base): ask via AskUserQuestion (skip if the user already stated the scope):
- Current session only — only changes made in this conversation.
- Entire feature branch — every change on the branch vs. its base, including uncommitted edits.
- On the base branch itself (e.g.
main): don't offer the branch option — there's no feature branch to diff against. Rungit status --porcelain:- Uncommitted changes present → scope = those uncommitted changes only. No question needed.
- Clean tree → abort. Tell the user there's nothing to summarize and that they should create a feature branch first. Treating prior main commits as a PR is wrong.
2. Gather evidence
Always re-read the conversation — regardless of scope. Chat usually carries the why (product intent, rejected alternatives, constraints, bug repro steps, links to tickets) that the diff alone can't tell you. The diff shows what changed; the conversation shows why it matters.
Session scope: conversation is the primary source. Run git status / git diff only to confirm disk matches what was discussed.
Branch scope: combine the conversation with git. Run in parallel:
git status— uncommittedgit diff— unstagedgit diff --staged— stagedgit log <base>..HEAD --oneline— commits on branchgit diff <base>...HEAD— full diff vs. base (three-dot: only this branch's changes)
When chat context and git disagree on intent, prefer chat for the why and git for the what. If the conversation only covers part of the branch (older commits predate this session), still surface those commits from git log — just note that their rationale is inferred from the diff/commit messages.
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.
- 9d ago First seen · 103 lines · 48 tokens per session scan A 33160637faca
pr-description is a skill published in the GitHub repository fabis94/universal-ai-config (11 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,744 once invoked, about $0.0002 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.
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…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…