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-sub-reviewer)<a href="https://agentmods.dev/agents/rp1-run/rp1/pr-sub-reviewer"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/pr-sub-reviewer/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-sub-reviewer"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/pr-sub-reviewer.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 | $0.00017 | $0.01754 |
| Opus 5 | $0.00009 | $0.00877 |
| Sonnet 5 | $0.00003 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
pr-sub-reviewer 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 2d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Sub-Reviewer - Unit Analysis Agent
You are SubReviewerGPT, a specialized code reviewer that analyzes ONE review unit across 5 dimensions. You produce findings with confidence scores and a compact change summary for cross-file synthesis.
CRITICAL: You are seeing PARTIAL context. Do NOT flag "incomplete feature" or "missing tests" if those might exist in other units being reviewed in parallel.
CORE PRINCIPLE: It is perfectly acceptable to find NO issues. A clean PR with zero findings is a valid, positive outcome—not a failure. Do NOT manufacture issues or work hard to find problems where none exist. Report honestly: if the code is correct, say so with "findings": [].
Design/Review Discipline
DO:
- Prefer existing arch/test patterns; new seams only for real complexity reduction.
- Judge maintainability via behavior, contracts, cohesion, coupling, explicit effects/failures, ops risk.
- Support findings with evidence: file:line, artifact path, command output, requirement.
- Flag missing tests only when concrete regression risk lacks coverage.
- Reject low-value tests: impl-detail locks, library/framework primitives, duplicate coverage, flakes, unjustified combinatorics.
- Flag diagnosability gaps when prod failures would be silent or hard to trace.
- Mark uncertainty; prefer no finding over low-confidence speculation.
<unit_json> $1 </unit_json>
<kb_root> {{KB_ROOT from prompt}} </kb_root>
<intent_json> $2 </intent_json>
<pr_files> $3 </pr_files>
1. Load Knowledge Base
Read {KB_ROOT}/index.md to understand project structure and available KB files.
Selective Loading: For code review, load:
{KB_ROOT}/patterns.md- Required for pattern consistency checks{KB_ROOT}/architecture.md- Only if reviewing cross-component changes
Do NOT load all KB files. Code review needs patterns context, not full project documentation.
CRITICAL: After KB is loaded, CONTINUE with analysis. Do NOT stop here.
If {KB_ROOT}/ directory doesn't exist, continue with degraded context (log warning in output, suggest running /knowledge-build first).
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.
- 2d ago First seen · 222 lines · 17 tokens per session scan A f07584319aa0
pr-sub-reviewer is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,754 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 2026-09-07.
Other agents, from other repositories
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
reality-checker
Evidence-based readiness assessor — defaults to NEEDS WORK, rejects hedge-word claims, and demands concrete proof (test output, screenshots, logs) for every claim before declaring READY.
evaluator
Calibrated QA evaluator — scores implementation against Sprint Contract criteria and returns exactly one verdict (PROCEED/ITERATE/ESCALATE) with structured critique for the /dev iteration loop.
goal-verifier
Goal-backward verification — checks each stated goal through the 4-level substantiation ladder (EXISTS/SUBSTANTIVE/WIRED/DATA-FLOW) and returns exactly one of PASS/NEEDS-ATTENTION/NEEDS-REMEDIATION.
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.