ffi-reviewer

ffi-reviewer is an agent for Claude Code from joelmoss/proscenium. It costs 0 tokens per session (432 once invoked), scanned A, original, MIT.

Review changes to the Ruby-Go FFI boundary for correctness.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/joelmoss/proscenium/ffi-reviewer
Clone the repo
git clone --depth 1 https://github.com/joelmoss/proscenium

Made for: Claude Code.

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 ffi-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/joelmoss/proscenium/ffi-reviewer.svg)](https://agentmods.dev/agents/joelmoss/proscenium/ffi-reviewer)
Your own site
<a href="https://agentmods.dev/agents/joelmoss/proscenium/ffi-reviewer"><img src="https://agentmods.dev/badge/agents/joelmoss/proscenium/ffi-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00432
Opus 5 $0.00000 $0.00216
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash c976dd5fafcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ffi-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.

.claude/agents/ffi-reviewer.md · 30 lines

What it actually says

FFI Bridge Reviewer

Review changes to the Ruby-Go FFI boundary for correctness.

When to use

When changes touch lib/proscenium/builder.rb, lib/proscenium/resolver.rb, or main.go.

Files to review

  • lib/proscenium/builder.rb — Ruby FFI struct and function definitions
  • lib/proscenium/resolver.rb — Ruby resolver that interfaces with Go via FFI
  • main.go — C struct definitions (in comment block) and exported Go functions

What to check

  1. Struct field alignment: Ruby FFI::Struct layouts must match the C struct definitions in main.go:
    • Result: success (bool/int), response (string/char*), content_hash (string/char*)
    • ResolveResult: success (bool/int), url_path (string/char*), abs_path (string/char*)
    • CompileResult: success (bool/int), messages (string/char*)
  2. Function signatures: attach_function declarations must match //export Go functions:
    • build_to_string(string, pointer) -> Result
    • resolve(string, pointer) -> ResolveResult
    • compile(pointer) -> CompileResult
    • reset_config() -> void
  3. Parameter order and types: Ensure Ruby FFI types (:string, :pointer, :bool, :void) correspond to Go C types (*C.char, C.int)
  4. Return value handling: Ruby side reads struct fields correctly (e.g. result[:success], result[:response])
  5. Memory management: FFI::MemoryPointer.from_string for config JSON, C.CString allocations in Go
  6. New functions: Any new //export function in Go must have a corresponding attach_function in Ruby, and vice versa
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. 2d ago First seen · 30 lines · 0 tokens per session scan A c976dd5fafcc

Subscribe to this mod's changes

ffi-reviewer is an agent published in the GitHub repository joelmoss/proscenium (104 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 432 tokens. 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 2026-09-01.