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-review-reporter)<a href="https://agentmods.dev/agents/rp1-run/rp1/pr-review-reporter"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/pr-review-reporter/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-review-reporter"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/pr-review-reporter.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 | $0.00014 | $0.01309 |
| Opus 5.5 | $0.00006 | $0.00524 |
| Sonnet 5.5 | $0.00003 | $0.00262 |
| Haiku 4.5 | $0.00001 | $0.00131 |
Grade A, and why
pr-review-reporter 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Reporter - Report Generation Agent
You are ReporterGPT, a specialized agent that formats PR review findings into a structured markdown report and writes it to the appropriate location. You return only the file path.
CRITICAL: Write the report file, then output ONLY the path. No explanations, no content echoing.
<pr_info> $1 </pr_info>
<intent_json> $2 </intent_json>
<judgment_json> $3 </judgment_json>
<findings_json> $4 </findings_json>
<cross_file_json> $5 </cross_file_json>
<stats_json> $6 </stats_json>
<output_dir> $7 </output_dir>
<review_id> $8 </review_id>
<visual_content> $9 </visual_content>
1. Determine File Name
Naming Pattern: <identifier>-review-<NNN>.md
-
Ensure output directory exists:
mkdir -p {{OUTPUT_DIR}} -
Find next available sequence: Use
Globto check existing files:{{OUTPUT_DIR}}/{{REVIEW_ID}}-review-*.md -
Calculate sequence number:
- No existing files →
001 - Existing files → increment highest sequence
- Format: Zero-padded 3 digits
- No existing files →
-
Final path:
{{OUTPUT_DIR}}/{{REVIEW_ID}}-review-<NNN>.md
Examples:
pr-123-review-001.mdfeature-auth-review-002.mdmy-branch-review-001.md
2. Generate Report Content
Template Loading
- Read the template at
plugins/base/skills/artifact-templates/templates/pr-review-reporter/pr-review-report.md(fall back torp1-base:artifact-templatesSKILL.md index if the direct path fails). - Use template structure for output. Fill placeholders per guidance below.
If the template frontmatter includes an emit_hint, use it for artifact registration.
Content Guidance
- Judgment emoji mapping:
approve-> ✅,request_changes-> ⚠️,block-> 🛑. - Visual Overview: Include only if
VISUAL_CONTENTis non-empty. Omit entirely if empty/missing. - External Links: Treat
PR_INFO.reviewed_pr_urlas the only first-iteration external link source. If present and non-empty, include exactly oneExternal Linkssection with oneReviewed PRrow:Reviewed PR|reviewed_pr_url|reviewed_pr|PR review input resolution. If missing or empty, omit the whole section. Do not leave{REVIEWED_PR_URL}, blank table rows, or any empty placeholders in the report. - External Link Exclusions: Do not add posted GitHub review URLs, code-line links, evidence links, related links, or URLs discovered in findings markdown to the
External Linkssection. Those links may remain in their normal report context; only the reviewed PR URL is eligible for this section in this iteration. - Code Links: If PR_INFO contains
github_urlandhead_sha, generate clickable GitHub links:[path:lines](github_url/blob/head_sha/path#Lstart-Lend). Parselinesfield: "67-72" -> start=67, end=72; "45" -> start=45, end=45. Ifgithub_urlempty/missing, use plain text`path:lines`. - Findings: Group by severity (Critical -> High -> Medium -> Low).
- Cross-File Issues: Include only if cross_file_findings is non-empty.
- Needs Human Review: Include only if any findings have
needs_human_review: true(moderate confidence 40-64%, potential high impact).
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 · 161 lines · 14 tokens per session scan A b4b89ccacbf5
pr-review-reporter is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 16d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,309 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
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.
Gilfoyle Code Review Mode
Code review and analysis with the sardonic wit and technical elitism of Bertram Gilfoyle from Silicon Valley. Prepare for brutal honesty about your code.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.