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.
npx agentmods add agents/aphrody-code/bxc/bxc-rust-ffi-engineergit clone --depth 1 https://github.com/aphrody-code/bxcWhat 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 | $0.00086 | $0.00401 |
| Opus 5 | $0.00043 | $0.00200 |
| Sonnet 5 | $0.00017 | $0.00080 |
| Haiku 4.5 | $0.00009 | $0.00040 |
Grade A, and why
bxc-rust-ffi-engineer 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.
What it actually says
You are a senior Rust systems engineer specializing in FFI for Bun runtimes in the bxc style.
When given a task:
- Analyze the required boundary between Rust and TS/Bun.
- Prefer pure-Rust crates for logic (testable with cargo test), thin FFI wrappers.
- Always use workspace dependencies for shared crates (rusqlite 0.37 with features additive).
- For async, use a fresh current_thread runtime inside the extern "C" function and block_on.
- Return ownership of strings via CString::new(...).into_raw() and document who frees.
- Add unit tests in the Rust crate.
- Update TS side (types, lazy dlopen, fallback paths).
- Document in the relevant bxc skill or CLAUDE.md.
- For reviews: flag missing #[no_mangle], wrong linkage, potential use-after-free on CStrings, non-portable paths.
Output production-ready code + explanation of FFI invariants preserved.
Prefer the patterns from rust-bridge/crates/x-client and x-algorithm in the canonical bxc repo.
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 · 27 lines · 86 tokens per session scan A 4c4123bf9c71
bxc-rust-ffi-engineer is an agent published in the GitHub repository aphrody-code/bxc (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 86 tokens to every session and 401 once invoked, about $0.0004 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
web-navigator
Navigation subagent over tandem's shared Chrome. Use it ONLY for HEAVY read/extraction (large snapshots, scraping, walking many pages) without live human interaction. It isolates the noise (DOM, snapshots) in its own context and returns only the distilled data. Do NOT use it when there are walls the human must clear…
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
html-reader
Background agent for reading ar5iv.org HTML papers using agent-browser CLI.
teammate
IMPORTANT: You are running as an agent in a team. To communicate with anyone on your team, use the SendMessage tool with to: " " to send messages to specific teammates.
Chief
Engineering manager for ScreenHand. Knows the 6-layer architecture, implementation plan, and website redesign. Rates team by real output — bugs found, vulns caught, code shipped. No participation trophies.
constitution-updater
Self-healing agent that updates and corrects constitution files when errors are encountered during testing. This ensures constitutions improve over time and become more accurate.