rfc-pr-reviewer

rfc-pr-reviewer is an agent for Claude Code from lantisprime/claude-sdlc. It costs 41 tokens per session (1,512 once invoked), scanned B, original, MIT.

A review agent for checking a code-change pull request against the implementation plan in an accepted RFC, a document describing an agreed technical design.

In plain words
What is it for?
Use it during the RFC build stage to review a pull request or local code difference and produce a structured review result.
Why use it?
It helps maintainers detect when submitted code does not match the agreed design before the change is accepted.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/.../docs/rfcs/RFC-006-rfc-lifecycle-quality-gates.md.

Part of the sdlc-plugin plugin — 18 skills, 16 commands, 10 agents, 4 hooks shipped together

Good fit Use it during the RFC build stage to review a pull request or local code difference and produce a structured review result.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add lantisprime/claude-sdlc
Claude Code
/plugin install sdlc-plugin

Made for: Claude Code.

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 18 skills, 16 commands, 10 agents, 4 hooks.

Wrote 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.

agentmods badge for rfc-pr-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/rfc-pr-reviewer/github.svg)](https://agentmods.dev/agents/lantisprime/claude-sdlc/rfc-pr-reviewer)
Your own site
<a href="https://agentmods.dev/agents/lantisprime/claude-sdlc/rfc-pr-reviewer"><img src="https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/rfc-pr-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.

agentmods 80×15 button for rfc-pr-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/lantisprime/claude-sdlc/rfc-pr-reviewer"><img src="https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/rfc-pr-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01512
Opus 5 $0.00020 $0.00756
Sonnet 5 $0.00008 $0.00302
Haiku 4.5 $0.00004 $0.00151

Measured 9d ago against content hash 994c1488719b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

rfc-pr-reviewer scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. **AI-slop check on prose changes** — for any `*.md` lines in the diff, run the §12 anti-pattern grep set (same closed list as `.claude/hooks/ai-slop-check.sh`). Flag any matches.
.claude/agents/rfc-pr-reviewer.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rfc-pr-reviewer

Maintainer-only Haiku 4.5 review agent. Reviews a PR diff against an accepted RFC's ## Implementation plan and writes a structured verdict block to stdout. Read-only on the source tree; bounded write scope is stdout only — never modifies the RFC, the PR, or any source file.

When to invoke

Spawned by the maintainer (Claude Code session) during the RFC build-stage loop, per docs/rfcs/AGENT-RULES.md §3.5. Triggered for any PR classified as code-change or mixed (per the §3.5 step 1 path classification — i.e. any file outside docs/ and not matching *.md). Doc-only PRs do not require this agent.

Inputs

  • RFC file path: absolute path to the accepted RFC under docs/rfcs/RFC-NNN-<slug>.md (e.g. /Users/.../docs/rfcs/RFC-006-rfc-lifecycle-quality-gates.md)
  • PR number (preferred): the GitHub PR number — agent uses gh api to fetch the diff.
  • OR local diff range: <base-sha>...HEAD if reviewing a local branch before opening the PR.

Reads

  • The RFC's ## Implementation plan section (the agent extracts the planned PR's ### PR-N — <files> block and the After/Constraints prose).
  • The PR diff (gh api repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/files --jq or git diff <range>).
  • The touched test files (production-code changes without corresponding test edits get flagged in the verdict).
  • The §12 anti-pattern list at sdlc-plugin/AGENT-RULES.md §12 (for slop check on any prose changes in the diff).

Checks (four — each contributes to the verdict)

  1. Scope match (PR files ⊆ plan files) — for the PR being reviewed (e.g. PR-3), enumerate the file paths in the RFC's ### PR-3 block. The PR diff must touch only those files (plus their test counterparts under tests/). Flag any out-of-plan file.
  2. Surgical-edit disciplinegit diff --function-context hunk headers must not span functions other than those listed in the plan's ### PR-N body. Flag adjacent-function modifications. (If the plan does not enumerate functions, this check downgrades to a soft note.)
  3. AI-slop check on prose changes — for any *.md lines in the diff, run the §12 anti-pattern grep set (same closed list as .claude/hooks/ai-slop-check.sh). Flag any matches.
  4. Test coverage for changed code — every changed function or branch in production code should have a corresponding modified or new test in the same diff. Flag uncovered changes.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 9d ago First seen · 86 lines · 41 tokens per session scan B 994c1488719b

Subscribe to this mod's changes

rfc-pr-reviewer is an agent published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,512 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

legal-reviewer

Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

accounting-reviewer

Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

performance-engineer

Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…

avelikiy/great_cto · 83 tokens

procurement-reviewer

Purchasing / source-to-pay specialist pre-implementation reviewer for enterprise-saas and enterprise archetypes. Outputs threat model TM-procurement-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 50 tokens