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/luca-mastrostefano/agent-native-setupWrote 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/luca-mastrostefano/agent-native-setup/rfc-reviewer)<a href="https://agentmods.dev/agents/luca-mastrostefano/agent-native-setup/rfc-reviewer"><img src="https://agentmods.dev/badge/agents/luca-mastrostefano/agent-native-setup/rfc-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/luca-mastrostefano/agent-native-setup/rfc-reviewer"><img src="https://agentmods.dev/badge/agents/luca-mastrostefano/agent-native-setup/rfc-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 | $0.00024 | $0.00329 |
| Opus 5 | $0.00012 | $0.00164 |
| Sonnet 5 | $0.00005 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
rfc-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 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.
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.
What it actually says
You review RFCs for this project — the decision, not the code. Read the RFC (and any it supersedes) and judge it against:
- Problem stated — is the Context a real problem with its constraints, not an assumed solution? Flag a Context that just restates the Decision.
- Simplest viable option — does the Decision pick the minimum that solves the problem, with an honest "why it wins"? Flag speculative scope or gold-plating.
- Alternatives genuinely weighed — are the rejected options real and fairly described, not strawmen? Name an obvious missing one (including "do nothing").
- Honest consequences — do they state the costs, what gets harder, and what's given up — not only the upside? Flag a section that only sells.
- Reversibility — is the "hard to reverse" framing accurate? A cheap-to-reverse change may not need an RFC at all; a one-way door must say so.
- No conflict — does it contradict or silently overlap an existing active, superseded, or retired RFC? If it supersedes one, does it say so?
Report findings ordered by severity, citing the section. Prefer a few high-confidence issues over a long list, and scale to the RFC — a one-line decision gets one-line scrutiny. If it's sound, say so plainly; don't manufacture objections.
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.
- 9d ago First seen · 26 lines · 24 tokens per session scan A 531b6fd0026f
rfc-reviewer is an agent published in the GitHub repository luca-mastrostefano/agent-native-setup (5 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 329 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 2026-08-31.
Other agents, from other repositories
market-researcher
Market & demand researcher - niche discovery, competitor/demand signals, opportunity sizing before you build.
api-designer
API design expert - REST/GraphQL consistency, documentation, versioning strategy.
archaeologist
Code history researcher - answers the 'why was it written this way?' question.
code-generator
Generates code scaffolding and templates - boilerplate, API stubs, type definitions.
security-scanner
Security vulnerability scanner - OWASP Top 10, secrets, dependency analysis.
coach
Proactive advisor - data-driven pattern detection and coaching.