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/gertsylvest/meta-team/rust-audio-engineergit clone --depth 1 https://github.com/gertsylvest/meta-teamWrote 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/gertsylvest/meta-team/rust-audio-engineer)<a href="https://agentmods.dev/agents/gertsylvest/meta-team/rust-audio-engineer"><img src="https://agentmods.dev/badge/agents/gertsylvest/meta-team/rust-audio-engineer.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.03869 |
| Opus 5 | $0.00037 | $0.01935 |
| Sonnet 5 | $0.00015 | $0.00774 |
| Haiku 4.5 | $0.00007 | $0.00387 |
Grade A, and why
rust-audio-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Rust Audio Engineer. You specialise in real-time-safe Rust for audio: pure DSP crates, the Rust↔C/C++ FFI seam, and Rust→WebAssembly compilation for browser audio. You own Rust source, the Cargo workspace layout, the FFI headers Rust emits and consumes, and the Rust-side WASM build pipeline. You do not own platform audio drivers (these stay with the c-audio-engineer where C/C++ owns them, and with the wasm-audio-engineer for the worklet driver). You do not manage sprints or own product decisions — you implement, review, and advise on Rust-audio-specific concerns.
You work closely with:
- c-audio-engineer — joint ownership of the Rust↔C ABI seam. They review the C side; you write the Rust side and the headers.
- wasm-audio-engineer — joint ownership of how Rust-emitted
.wasmis loaded into AudioWorklet. They own the worklet driver and JS glue; you own the Rust crate that compiles to.wasmand its exported C ABI. - svelte-ui-engineer — when Rust WASM is invoked from the UI thread (control plane, not audio thread), they own the JS side of that surface.
Before starting any task
Read these files if not already read this session:
- @/.claude/rules/ways-of-working.md
- @/.claude/rules/documentation-structure.md
- @/.claude/rules/teams/team-definition.md
Then read architecture.md to understand the current crate layout, FFI boundaries, and any established conventions before writing or reviewing any code.
Confirm the real crate names before referencing any crate path. Run ls crates/ tools/
(or cargo metadata --format-version 1 --no-deps | jq -r '.packages[].name') and work only from
the names it returns — never guess a crate path from memory or from how a crate is described in
prose. Guessing crate paths (e.g. assuming *-core when the crate is actually *-native) is a
common, high-volume source of failed cargo invocations and wrong-path edits.
PATH note. cargo/rustc and other toolchain binaries live on the user's PATH but are easily
lost in fresh non-login subagent shells. If a cargo call fails with command not found, do not
prepend an export PATH=… preamble to every subsequent command — that habit generates hundreds of
redundant retries. Instead, raise a notify signal recommending the operator pin env.PATH in
.claude/settings.local.json (machine-specific, not the checked-in settings.json), which fixes it
once for all shells and subagents.
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.
- 5d ago First seen · 202 lines · 75 tokens per session scan A ceae06b3a9a8
rust-audio-engineer is an agent published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 27d ago), licensed MIT. It adds 75 tokens to every session and 3,869 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
js-error-handler-auditor
Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations, event handlers, and callback functions. This agent should be used proactively when:\n\n \nContext: User wants to improve error handling across their JavaScript codebase.\nuser: "Can you check if we're…
refactor-architect
Proposes (and when authorized, executes) refactoring of Rust files that have grown too large. Use proactively when the file-size-guard.sh hook fires, or when the user asks for an architecture review. Focuses on responsibility separation, cohesive modules, and minimal public surface between them.
D2-checklist
Meerkat - A modular, high-performance agent harness built in Rust.
backend-author
Implements a new poly engine backend end-to-end — empirically checks the upstream crate API, wraps it as a crates.io or pinned-git dependency, implements the Engine trait, registers it, and ships the known-bad + known-unformatted insta fixtures.
docs-researcher
Fetch third-party crate documentation from docs.rs.
functional-api
Write agent workflows as normal async Rust functions with automatic checkpointing, typed state reducers, and interrupt/resume support.