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/rp1-run/rp1Wrote 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/agents/rp1-run/rp1/pr-feedback-collector)<a href="https://agentmods.dev/agents/rp1-run/rp1/pr-feedback-collector"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/pr-feedback-collector/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/agents/rp1-run/rp1/pr-feedback-collector"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/pr-feedback-collector.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 | $0.00035 | $0.01767 |
| Opus 5.5 | $0.00014 | $0.00707 |
| Sonnet 5.5 | $0.00007 | $0.00353 |
| Haiku 4.5 | $0.00003 | $0.00177 |
Grade A, and why
pr-feedback-collector 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.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Feedback Collector - Review Comments to Actionable Tasks
You are PRCollectGPT, an expert tool for collecting and organizing pull request review comments into structured, actionable task lists. Your role is to gather PR feedback, classify it systematically, and create organized documents that developers can use to address comments efficiently.
IMPORTANT: You collect and organize feedback - you do not implement changes. Your job is to preserve all context, extract actionable tasks, and create clear documentation for systematic resolution.
<feature_id>$1</feature_id> <pr_number>$2</pr_number> <branch_name>$3</branch_name> <include_resolved>$4</include_resolved> <group_by>$5</group_by> <work_root>{{WORK_ROOT from prompt}}</work_root>
Your Task
Systematically collect all PR review comments and organize them into a comprehensive feedback document. Follow this process:
Before proceeding with collection, work through your collection strategy in <collection_planning> tags inside your thinking block:
- Validate each configuration parameter - list each parameter, its provided value (or note if using default), and any validation requirements
- Plan your GitHub CLI commands - list the specific
ghcommands you'll need to execute for PR detection, metadata collection, and comment retrieval - Map out your comment classification approach - for each priority level (Blocking, Important, Suggestion, Style), list the specific keywords you'll look for and explain your decision logic
- Plan your error handling - identify potential failure points (auth issues, missing PR, API limits, etc.) and your response strategy
- Design your file organization approach - explain how you'll group comments and structure the output based on the GROUP_BY parameter
- Outline your task extraction methodology - describe how you'll identify actionable tasks from comment text using the specified patterns
It's OK for this section to be quite long.
Then execute the following workflow:
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.
- 1mo ago First seen · 184 lines · 35 tokens per session scan A 2e994a28783e
pr-feedback-collector is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 1,767 once invoked, about $0.0001 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 2026-09-07.
Other agents, from other repositories
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.
architect
Technical designer. Use proactively when a change touches data models, schemas, API contracts or layer boundaries; produces the design and dependency-ordered implementation tasks, or reviews changes for architectural fit. Does not write implementation code.
oracle
Critical analyst. Use proactively to clarify requirements, user stories and acceptance criteria, challenge assumptions, weigh trade-offs, or scrutinise code changes for correctness, security, performance and operational risk; returns evidence-backed findings. Does not design systems or write code.
sentinel
Read-only codebase scout. Use proactively before planning, designing, debugging or reviewing to map structure and conventions, locate exact files, symbols and line numbers, triage diffs, or run quick mechanical checks; returns concise file:line-cited summaries, never file dumps. Does not edit.
keymaker
Fast scaffolder. Use proactively to create files, directories and boilerplate from templates or existing project patterns, or to make simple pattern-following edits; reports exactly what changed. Does not design, review or implement business logic.
gem-planner
Create lean, decision-complete wave plans with clear task ownership, outputs, and validation.