Borrowing it
Nothing to install: this file belongs to andrzejchm/fdb. 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/andrzejchm/fdb/main/.agents/skills/managing-pull-requests/SKILL.mdgit clone --depth 1 https://github.com/andrzejchm/fdbWrote 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/andrzejchm/fdb/managing-pull-requests)<a href="https://agentmods.dev/skills/andrzejchm/fdb/managing-pull-requests"><img src="https://agentmods.dev/badge/skills/andrzejchm/fdb/managing-pull-requests/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/andrzejchm/fdb/managing-pull-requests"><img src="https://agentmods.dev/badge/skills/andrzejchm/fdb/managing-pull-requests.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 | $0.00137 | $0.01155 |
| Opus 5.5 | $0.00055 | $0.00462 |
| Sonnet 5.5 | $0.00027 | $0.00231 |
| Haiku 4.5 | $0.00014 | $0.00115 |
Grade A, and why
managing-pull-requests 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 24d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide for the full PR lifecycle: branch, open, review-fix, merge. Contains rules across 3 topics. code-reviewing is a separate skill — load it for the actual review engine; this skill only covers triaging and applying its findings. Waiting on CI, a deployment, or a review run is a separate skill too — load polling-monitoring.
Topics
| # | Topic | Covers | Reference |
|---|---|---|---|
| 1 | Branching and opening | Branch naming, PR title/description format, draft vs ready, PR type rules, updating an existing PR | BRANCHING-AND-OPENING.md |
| 2 | Review and fix | Resolving review threads, CI triage, the fixing-PR workflow, the review-fix polish loop | REVIEW-AND-FIX.md |
| 3 | Merging | Merge-blocker diagnosis, squash-merge steps, linked-ticket status update, worktree cleanup | MERGING.md |
Quick Checklist
Copy and track for a full PR lifecycle:
- [ ] Branch named CU-<id>/<type>/<slug> (BRANCHING-AND-OPENING.md)
- [ ] The project's check and test commands both pass before opening
- [ ] PR opened with a real title/description, ready unless draft explicitly requested
- [ ] Reviews + CI triaged, VALID-FIX items fixed, threads resolved (REVIEW-AND-FIX.md)
- [ ] The project's check and test commands both green before every push
- [ ] Merge gate checked: mergeable=MERGEABLE, mergeStateStatus=CLEAN, reviewDecision=APPROVED, all checks green (MERGING.md)
- [ ] Squash-merge with --delete-branch
- [ ] Linked ticket status set manually (nothing does this automatically)
- [ ] Worktree removed only if git status is clean
Hard Rules
- NEVER use placeholder PR titles ("Update feature") or auto-generated branch-name titles.
- NEVER skip the project's check command (format, lint, typecheck) AND its test command (unit tests) before opening a new PR or before any push, scoped to the touched packages (e.g.
task check:pkg -- <pkg>andtask test:pkg -- <pkg>in projects using the agentkit taskfile recipe). Run them as two separate required commands: a check command that runs no tests is not a substitute for the test command. - NEVER create stacked implementation PRs — merge the current one before opening the next dependent one.
- ALWAYS squash-merge with
--delete-branch. Never merge-commit, rebase-merge, or merge a draft/fork PR. - ALWAYS resolve or reply to every review thread before considering a PR merge-ready (REVIEW-AND-FIX.md Step 6).
- ALWAYS close every finding (review comment, CI observation, caveat, out-of-scope issue) one of two ways: fix it in the same PR when the fix is minimal and obvious, or report it to the user in chat with a suggested follow-up ticket (title + one-line why — never auto-created). PRs are read only by agents, never by people — a finding left only in a PR description, review reply, or thread disappears unnoticed.
- ALWAYS update the linked ticket's status manually after merge — nothing does this automatically (MERGING.md).
- Follow
polling-monitoring's bounded check/report/sleep/check pattern before any wait loop on CI, a deployment, or a review run — neverwatch,tail -f, or shellwhileloops. - Apply
humanizing-ai-text's rules to every PR title, description, review reply, and status update you write — no em dashes, no chatbot filler, no sycophantic openings.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago First seen · 58 lines · 137 tokens per session scan A 075fda405b81
managing-pull-requests is a skill published in the GitHub repository andrzejchm/fdb (46 stars, last pushed 12d ago), licensed MIT. It adds 137 tokens to every session and 1,155 once invoked, about $0.0005 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 2026-10-01.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…