proscenium: Agent for Claude Code

.claude/agents/ffi-reviewer.md

ffi-reviewer is an agent for Claude Code from joelmoss/proscenium. It costs 46 tokens per session (552 once invoked), scanned A, original, MIT.

A code reviewer for the boundary between Ruby and Go, where the two languages exchange data and function calls through a foreign-function interface (FFI).

In plain words
What is it for?
Use it when changing the listed Ruby resolver or builder files, the Go entry point, or any Ruby–Go integration code.
Why use it?
It catches mismatched data layouts, function signatures, parameter types, and return values that can cause incorrect results or crashes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is joelmoss/proscenium's own configuration. It tells Claude Code how to work on proscenium itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything proscenium configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joelmoss/proscenium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joelmoss/proscenium/master/.claude/agents/ffi-reviewer.md
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/github.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/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 ffi-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/joelmoss/proscenium/ffi-reviewer"><img src="https://agentmods.dev/badge/agents/joelmoss/proscenium/ffi-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00046 $0.00552
Opus 5.5 $0.00018 $0.00221
Sonnet 5.5 $0.00009 $0.00110
Haiku 4.5 $0.00005 $0.00055

Measured 20d ago against content hash 7637cc433ec8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 20d 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 · 36 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/request.rb, lib/proscenium/builder.rb, or main.go.

Files to review

  • lib/proscenium/builder/request.rb — ffi_lib and the attach_function declarations
  • lib/proscenium/builder.rb — the result structs, and the calls that read and free them
  • main.go — C struct definitions (in the comment block) and the 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 (pointer/char*), content_hash (pointer/char*)
    • ResolveResult: success (bool/int), url_path (pointer/char*), abs_path (pointer/char*)
    • CompileResult: success (bool/int), messages (pointer/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
    • free_cstr(pointer) -> 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: every string field is read through read_and_free in builder.rb, never as :string
  5. Memory management: FFI::MemoryPointer.from_string for config JSON; each C.CString Go returns is freed exactly once by free_cstr, since the Go runtime cannot collect it
  6. New functions: Any new //export function in Go must have a corresponding attach_function in Request, and vice versa. Keep every reference to the library inside Request, never in builder.rb's class body (see the Puma fork gotcha in AGENTS.md)
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. 20d ago Changed · +6 lines · +46 tokens per session 7637cc433ec8
  2. 2mo 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 yesterday), licensed MIT. It adds 46 tokens to every session and 552 once invoked, about $0.0002 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 2026-09-01.

Related

ffi-reviewer compared with agents from other repositories

ffi-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ffi-reviewerjoelmoss/prosceniumAgent104yesterdayMITA46Claude Code
compiler-reviewreact/reactAgent252kyesterdayMITA42Claude Code
go-revieweraffaan-m/ECCAgent298k4d agoMITA37Claude Code, Kiro
code-reviewerrootstrap/rails_api_baseAgent6342d agoMITA47Claude Code
pr-size-checkerrootstrap/rails_api_baseAgent6342d agoMITA50Claude Code
ruby-reviewerTheBeardedBearSAS/claude-craftAgent1073d agoMITA48Claude Code
Golang Code Review Agentcanonical/copilot-collectionsAgent323d agoApache-2.0A25Claude Code