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.
git clone --depth 1 https://github.com/ihudak/ihudak-claude-pluginsWrote 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/ihudak/ihudak-claude-plugins/prose-review-pr)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/prose-review-pr"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prose-review-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/commands/ihudak/ihudak-claude-plugins/prose-review-pr"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prose-review-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 | $0.00074 | $0.01953 |
| Opus 5 | $0.00037 | $0.00977 |
| Sonnet 5 | $0.00015 | $0.00391 |
| Haiku 4.5 | $0.00007 | $0.00195 |
Grade A, and why
prose-review-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 5d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review documentation changes from a pull request
Reviews the markdown files changed in a pull request against the active prose style rules — the plugin's vendor-neutral baseline, plus your organization's overlay when one is configured. Outputs a structured violation report.
Arguments
The command receives its input via $ARGUMENTS. Accepted formats:
| Format | Example | Behaviour |
|---|---|---|
| PR number | 9089 |
Finds merge commit or remote branch for that PR |
| Branch name | feat/improve-install-guide |
Diffs the branch against main |
--repo <path> |
--repo /workspace/product-docs |
Override the repo path (default: current working directory) |
--doc-type <type> |
--doc-type product-docs |
Passed to prose-style-checker for severity calibration (default: product-docs) |
--rules <path> |
--rules ~/style/rules |
Override overlay discovery; passed to prose-style-checker as rules_path |
Arguments can be combined: 9089 --repo /workspace/product-docs.
If no arguments are provided, ask the user for a PR number or branch name.
Procedure
1. Parse arguments
Extract from $ARGUMENTS:
- target: the PR number (all digits) or branch name (anything else that is not a flag).
- repo_path: value after
--repo, or the current working directory if absent. - doc_type: value after
--doc-type, orproduct-docsif absent. - rules_path: value after
--rules, or absent.
If no target is found, ask the user: "Please provide a PR number or source branch name."
2. Resolve changed files
Run every git command with git -C <repo_path>.
2a. If target is a PR number
# Look for the merge commit in ALL branches/tags
git -C <repo_path> log --all --oneline --grep="Pull request #<NUMBER>:" | head -5
Repositories that use GitHub's default merge subject line record it differently — if
the search above finds nothing, retry with --grep="(#<NUMBER>)" before falling
through to the branch search.
- Merge commit found (PR is merged):
- Extract the commit SHA.
- Get the diff:
git -C <repo_path> diff <SHA>^..<SHA> --name-only -- '*.md' - This gives the list of changed markdown files.
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.
- 5d ago First seen · 215 lines · 74 tokens per session scan A 144ccf6152cb
prose-review-pr is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,953 once invoked, about $0.0004 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 2026-09-05.
Other commands, from other repositories
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
watch
You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.
infogenius
Research-First Image Generation - Facts → Visual Prompt → High-Quality Image.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.