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 olehsvyrydov/AI-development-team --skill pull-requestgit clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/olehsvyrydov/ai-development-team/pull-request)<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/pull-request"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/pull-request/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/olehsvyrydov/ai-development-team/pull-request"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/pull-request.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 | $0.00078 | $0.01190 |
| Opus 5.5 | $0.00031 | $0.00476 |
| Sonnet 5.5 | $0.00016 | $0.00238 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
pull-request 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 today.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull requests — nothing is left dangling
A PR is finished when every question raised on it has an answer and every check that gates it has actually run. Both halves get skipped in the same way: by reading a summary instead of the thing itself.
The rule: never leave a review conversation open
Every review thread on a PR must be resolved before merge — no exceptions, including threads you disagree with and threads that have become obsolete. An open thread is an unanswered question, and a merged PR with open threads tells the next reader that nobody decided.
Resolving does not mean agreeing. There are exactly three honest outcomes, and each needs a reply before the thread is resolved:
| Outcome | Reply must say |
|---|---|
| Fixed | which commit, and what now enforces it (the symbol, not the intention) |
| Won't fix | why, specifically — cost, scope, or a rule that outranks it — not "by design" |
| Obsolete | why it no longer applies, e.g. the code it names was deleted |
Resolving silently is the failure mode to avoid: it looks identical to fixing it, and the reviewer cannot tell which happened.
Check for threads with the API — the PR page summary and gh pr view do not list unresolved
threads, so a PR can look clean while carrying several:
gh api graphql -f query='
{ repository(owner:"OWNER", name:"REPO") {
pullRequest(number:NN) {
reviewThreads(last:60) { nodes { id isResolved isOutdated path
comments(last:1){nodes{author{login} body}} } }
} } }' --jq '.data.repository.pullRequest.reviewThreads.nodes[]
| select(.isResolved==false) | "\(.path) | \(.comments.nodes[0].body[0:160])"'
Reply, then resolve:
gh api graphql -f query='mutation { addPullRequestReviewThreadReply(
input:{pullRequestReviewThreadId:"THREAD_ID", body:"..."}) { clientMutationId } }'
gh api graphql -f query='mutation { resolveReviewThread(
input:{threadId:"THREAD_ID"}) { thread { isResolved } } }'
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.
- today First seen · 95 lines · 78 tokens per session scan A 643c1cde8713
pull-request is a skill published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,190 once invoked, about $0.0003 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 2026-10-19.
Other skills, from other repositories
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
ln-61-repository-publisher
Commits, pushes and remotely verifies authorized repository changes; does not create releases.
merge-queue
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
review-comment
Use when operating as the Fabrik Review comment reviewer. This skill guides applying user decisions on review findings — fixing issues, dismissing false positives, or deferring items — then committing and pushing without signaling stage completion.