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.
curl -O https://raw.githubusercontent.com/BloomBooks/BloomDesktop/master/.github/prompts/bloom-make-pr-comment-plan.prompt.mdgit clone --depth 1 https://github.com/BloomBooks/BloomDesktopWrote 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/commands/bloombooks/bloomdesktop/bloom-make-pr-comment-plan)<a href="https://agentmods.dev/commands/bloombooks/bloomdesktop/bloom-make-pr-comment-plan"><img src="https://agentmods.dev/badge/commands/bloombooks/bloomdesktop/bloom-make-pr-comment-plan.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00503 |
| Opus 5 | $0.00006 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
bloom-make-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 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.
What it actually says
-
if I didn't tell you the name of the document, use the askQuestions tool to ask me. Always include the option "append or create pr-comments.md". If there is already a "pr-comments.md", then also offer one with a unique name that we don't have yet, like "pr-comments-2.md". Do this quickly so that I can leave while you work on the rest.
-
Find the pr. Use the gh tool to determine the PR associated with the current branch.
-
Collect up comments that do that have a reply. Do not rely only on native GitHub review threads. Also inspect the PR's reviews and review bodies for Reviewable-imported comments or discussion summaries, because those may not appear in
reviewThreadseven when the review says it contains many unresolved comments. Treat those Reviewable comments as part of the PR feedback you need to process. -
for each issue, add some lines like this:
Fred Flintstone review 3918647127
1. foo should be bar
Link: https://reviewable.io/reviews/BloomBooks/BloomDesktop/7621#-On-YsWVBDGHZLABoBtc:-On3jl8a-ol2j7BjS4fE:b-nlm6k9 Relevant code locations: bedrock.ts, line 52.
What they said: | The foo here should be bar, shouldn't it? <-- verbatim quote. Do not paraphrase.
Evaluation: Bar would't be bad, and we can make this change cheaply. The complication is that we already have a bar.
Action Proposals:
- Change foo to baz <-- proposed
- Change foo to bar2
- Say that prefers to stick with foo.
- Proposed Reply: "[model name]: It turns out "bar" is already in use, so I've changed to "baz". <--- do not be chatty, just state what you did (or would do)
User Decision: <-- user will fill this in later Reply:
- Reply successfully posted (check off when posted to github or Reviewable):
Leave the "decision:" and "reply" lines there for a future step in our process.
When you answer, prefix your response with the name of your model, e.g. [hall9000].
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 · 41 lines · 12 tokens per session scan A cfeaa1c6c918
bloom-make-pr-comment-plan is a command published in the GitHub repository BloomBooks/BloomDesktop (44 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 503 once invoked, about $0.0001 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 2026-09-06.
Other commands, from other repositories
portaljs-define-schema
Define a dataset's metadata profile — infer a Frictionless Table Schema from its data, add Data Package metadata (license, sources, keywords), and write it into datasets.json so the showcase renders a typed field table. Extend or customize via the L0→L3 profile ladder.
pptx
Create, update, or manage PowerPoint slide decks.
vlm-ocr
Run the vlm-ocr skill on the task below. It has three phases: evaluate (compare candidate OCR systems against stratified human ground truth and pick one on measured CER/WER), run (build and execute the production VLM-OCR pipeline — model selection, image handling, prompts, architecture, batching, accuracy evaluation…
PRD Generation
Generate comprehensive Product Requirements Document from epic description.
brainstorm
Design-first ideation workflow that explores user intent, clarifies constraints, proposes approaches, and produces an approved design document before planning.
docai-classify
Build and use a Document Intelligence classifier — train a classifier to identify document types and split multi-document files.