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 arcasilesgroup/ai-engineering --skill ai-prgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-pr)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-pr"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-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.
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-pr"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-pr.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 | $0.00174 | $0.04172 |
| Opus 5.5 | $0.00070 | $0.01669 |
| Sonnet 5.5 | $0.00035 | $0.00834 |
| Haiku 4.5 | $0.00017 | $0.00417 |
Grade A, and why
ai-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 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-pr — carry the local main to a reviewed pull request
This is the one place in the framework where a push is legitimate. Until then the
work sits in the local main as one merge commit per feature, and origin/main
has not moved. Run the phases below in order and report what each one did; the
verb the human used decides how far the run goes — open stops after Phase 3,
finish/land/merge it continues through Phase 6 (see The ask). Read AGENTS.md
and the commit/PR conventions
in CONTRIBUTING.md first — they own the branch model and the title/changeset
rules this skill assumes, and nothing here repeats them.
The ask — the verb the human uses decides the run
- The verb decides how far the run goes, and nothing else does. Read the
words before any command runs, and print the shape as the first line of the
run:
- "open", "open the pull request", "make the PR" — Phases 1-3 run and the
run stops there:
ai-pr: opened <branch> — not merging.Open the pull request only is the open mode, and it never merges — no merge command, no auto-merge, and no Phase 6. - "finish", "land", "merge it", "get the PR merged", "run the full PR
loop" — the run carries the whole loop: cut, push, open, watch, fix, and
through the merge. Print
ai-pr: finishing <branch> — open, watch, merge.
- "open", "open the pull request", "make the PR" — Phases 1-3 run and the
run stops there:
- An ambiguous ask is the open one. When the words name neither shape, the run opens the pull request only and stops; the merge is the shape the human must name, never the one inferred.
- A green pull request is not a request to merge it. The merge happens because the human said finish, land or merge it — asking for this skill with a finish verb is the request to land the pull request — never because the checks came back green. Both the open ask and the ambiguous ask stop before Phase 6.
- A session that is still building never pushes. Only this step, the one the
human triggered, pushes, and only after every session has closed into the local
main.
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 · 357 lines · 174 tokens per session scan A bbe223f3cec0
ai-pr is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed yesterday), licensed Apache-2.0. It adds 174 tokens to every session and 4,172 once invoked, about $0.0007 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 2026-10-05.
Other skills, from other repositories
ai-agents-generation-and-release
Operate the ai-agents generation and release machinery, covering the seven buildall.py generators, generateagents.py, the drift gates, the version-free plugin manifests, and the npm publish path. Use when you say regenerate the mirrors, run the drift checks, why is the plugin version gate red, release the npm cli. Do…
ship
Run the four pre-flight checks, then create the PR or validate a contributor branch without touching it. Use when you say ship it, ship this branch, or run pre-flight and open the PR, and run it after review. Do NOT use to open a PR without the gates (use push-pr), and do NOT use to run the review axes themselves (use…
merge-resolver
Resolve merge conflicts by analyzing git history and commit intent. Handles PR conflicts, branch conflicts, and session file conflicts with automated resolution for known patterns. Use when you say "resolve merge conflicts", "fix conflicts on this branch", "PR has conflicts with main", "can't merge due to conflicts"…
git-advanced-workflows
Advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog. Use when managing complex Git histories, collaborating on feature branches, or recovering from repository issues. Use when you say "rebase my branch", "cherry-pick a commit", "find the breaking commit", "recover lost commits", or…
chestertons-fence
Investigate historical context of existing code, patterns, or constraints before proposing changes. Automates git archaeology, PR/ADR search, and dependency analysis to prevent removing structures without understanding their purpose. Use when you ask "why does this code/constraint exist", "is it safe to remove this".…
ai-agents-change-control
Change control for this repo. Classify a change (docs-only, investigation-only, code, plugin content, hook, workflow, ADR governance), map each class to the gates it triggers, and hold the non-negotiables with the incident behind each rule. Use when you say classify this change, what gates does this change trigger…