BloomDesktop: Skill for Claude Code

.claude/skills/pr-comment-plan/SKILL.md

pr-comment-plan is a skill for Claude Code from BloomBooks/BloomDesktop. It costs 92 tokens per session (699 once invoked), scanned A, original, MIT.

A Markdown planning document for collecting every unanswered comment on the current pull request, with the original quote, an assessment, proposed actions, and space for a decision.

In plain words
What is it for?
Use it to inspect a pull request's open review comments, decide how to handle each one, and prepare an offline response plan.
Why use it?
It keeps a large batch of review feedback in one place so you can sort through it before replying or changing code.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions AGENTS.md.

This is BloomBooks/BloomDesktop's own configuration. It tells Claude Code how to work on BloomDesktop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything BloomDesktop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BloomBooks/BloomDesktop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BloomBooks/BloomDesktop/master/.claude/skills/pr-comment-plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/BloomBooks/BloomDesktop

Made for: Claude Code.

Wrote 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.

agentmods badge for pr-comment-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/pr-comment-plan/github.svg)](https://agentmods.dev/skills/bloombooks/bloomdesktop/pr-comment-plan)
Your own site
<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/pr-comment-plan"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/pr-comment-plan/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.

agentmods 80×15 button for pr-comment-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/pr-comment-plan"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/pr-comment-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.00699
Opus 5.5 $0.00037 $0.00280
Sonnet 5.5 $0.00018 $0.00140
Haiku 4.5 $0.00009 $0.00070

Measured 1mo ago against content hash ab7a5fd53cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-comment-plan 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 1mo 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.

.claude/skills/pr-comment-plan/SKILL.md · 58 lines

What it actually says

PR comment plan

The job: gather the PR's unanswered review feedback into one Markdown document the developer can read, decide on, and hand back. Nothing is replied to or changed in this skill; the document is the deliverable. (Replying happens later, through reviewable-replies for Reviewable threads or gh for GitHub threads.)

  1. Pick the document name. If the user did not name one, ask, offering "append to or create pr-comments.md" and, if that file already exists, a fresh unique name such as pr-comments-2.md. Ask this first and quickly so the user can leave while you work.

  2. Find the PR for the current branch with gh (gh pr view --json number,url). If there is none, ask for a URL.

  3. Collect the comments that have no reply. Do not rely only on GitHub's reviewThreads. Also read the PR's reviews and review bodies: Reviewable-imported comments and discussion summaries often appear only there, even when the review says it contains many unresolved comments. Treat those as part of the feedback to process.

  4. Write one block per comment, in this shape:

    ----------------------
    ## Fred Flintstone review 3918647127
    
    ### 1. foo should be bar
    
    Link: <https://reviewable.io/reviews/BloomBooks/BloomDesktop/7621#-On-YsWVBDGHZLABoBtc>
    Relevant code locations: bedrock.ts, line 52.
    
    What they said:
    | The foo here should be bar, shouldn't it?      <-- verbatim quote; never paraphrase
    
    Evaluation:
    Bar wouldn't be bad, and the change is cheap. The complication is that we already have a bar.
    
    Action Proposals:
    1. Change foo to baz                             <-- the proposed one first
    2. Change foo to bar2
    3. Say that <reviewer> prefers to stick with foo.
    
    - Proposed Reply: "[<attribution tag>] "bar" is already in use, so I've changed to "baz"."
                                                     <-- not chatty; state what you did or would do
    
    User Decision:                                   <-- the developer fills this in later
    Reply:
    
    - [ ] Reply successfully posted (tick when posted to GitHub or Reviewable)
    -------------------
    

    Leave the User Decision: and Reply: lines empty; a later step in the process fills them. The proposed reply starts with the team attribution tag (TEAM-AGENTS.md, "Attribution"), since it will be posted under the developer's account.

Changes

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.

  1. 1mo ago First seen · 58 lines · 92 tokens per session scan A ab7a5fd53cdb

Subscribe to this mod's changes

pr-comment-plan is a skill published in the GitHub repository BloomBooks/BloomDesktop (43 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 699 once invoked, about $0.0004 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 2026-09-19.

Related

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.

Yeachan-Heo/oh-my-claudecode · 47 tokens

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.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 tokens

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.

Gentleman-Programming/engram · 37 tokens

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.

daymade/claude-code-skills · 105 tokens

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…

umputun/revdiff · 248 tokens