Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gertsylvest/meta-teamnpx agentmods add skills/gertsylvest/meta-team/rust-rt-auditWrote 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/skills/gertsylvest/meta-team/rust-rt-audit)<a href="https://agentmods.dev/skills/gertsylvest/meta-team/rust-rt-audit"><img src="https://agentmods.dev/badge/skills/gertsylvest/meta-team/rust-rt-audit/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/skills/gertsylvest/meta-team/rust-rt-audit"><img src="https://agentmods.dev/badge/skills/gertsylvest/meta-team/rust-rt-audit.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 | $0.00079 | $0.00820 |
| Opus 5 | $0.00039 | $0.00410 |
| Sonnet 5 | $0.00016 | $0.00164 |
| Haiku 4.5 | $0.00008 | $0.00082 |
Grade A, and why
rust-rt-audit 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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Real-Time Audit
Verify that a Rust DSP crate respects the real-time-safety rules:
- The crate is
#![no_std]and does not depend onalloc. - The crate uses
panic = "abort"so panics cannot unwind across an FFI or worklet boundary. - No clippy-detectable panic-prone constructs (
unwrap,expect, slice indexing, integer overflow) are present. - No banned heap/blocking constructs (
Vec::,Box::,Mutex,format!,println!, etc.) appear in the source. - The compiled LLVM-IR contains no calls to
__rust_alloc/__rust_realloc/__rust_dealloc.
The first four are cheap and run in seconds. The fifth is the authoritative check — a clean grep can lie, but an IR with no allocator symbols cannot.
Requirements
- rustup with a stable toolchain.
- cargo (bundled with rustup).
- The crate being audited must compile.
Optional but recommended:
clippycomponent (rustup component add clippy) for the lint pass. The script skips clippy cleanly if it is missing.
Instructions
The argument is in $ARGUMENTS. Pass it directly to the audit script:
bash "$(dirname "$0")/audit.sh" $ARGUMENTS
The argument is the path to the crate directory (the one containing Cargo.toml).
Output sections
| Section | What it reports |
|---|---|
NO_STD |
Whether #![no_std] is declared in src/lib.rs |
NO_ALLOC_DEP |
Whether the crate has any dependency on alloc (direct or via Cargo.toml) |
PANIC_ABORT |
Whether panic = "abort" is set in the release profile |
CLIPPY |
Lint results from a curated set of panic/allocation-detecting lints |
HOT_PATH_GREP |
Grep hits for banned constructs in src/**.rs |
LLVM_IR_ALLOC |
Whether __rust_alloc* symbols appear in the release LLVM-IR |
Typical usage
# Audit a single DSP crate
bash audit.sh ./rust/audio-dsp
# Audit every DSP crate in a workspace
for crate in rust/dsp-*; do bash audit.sh "$crate"; done
What to look for
NO_STDfailing is a structural problem — the crate should be split so DSP code lives in ano_stdcrate and anystd-dependent code moves to a sibling crate.NO_ALLOC_DEPfailing means a transitive dependency pulled inalloc. Usecargo tree -e featuresto find the culprit and either gate it behind a feature flag or replace it.PANIC_ABORTfailing is a one-lineCargo.tomlfix.CLIPPYorHOT_PATH_GREPhits require code changes — see the agent profile's Real-Time-Safe Rust section for the rationale and the safe replacements.LLVM_IR_ALLOCfailing despite a clean source grep usually means a third-party crate is allocating.cargo tree+ the IR's call site (look at the function name precedingcall __rust_alloc) identify the source.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 67 lines · 79 tokens per session scan A fd9868bf81fc
rust-rt-audit is a skill published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 820 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 skills, from other repositories
edge-python
Write, run, test and package Edge Python programs with the edge CLI. Use when editing .py files in an Edge Python project or when the user asks for Edge Python code.
cargo-fuzz
Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects. Covers cargo fuzz init, the nightly toolchain requirement, fuzztarget! harnesses, Arbitrary-derived structured inputs, sanitizer options, cargo fuzz coverage, and reproducing a crash artifact. Use when fuzzing a Rust crate, writing a…
check-impl
Implementation verification - runs format, lint, test, and build checks on the workspace.
mutation-test
Run mutation tests with cargo-mutants to verify test quality. Reports caught, missed, and timed-out mutants.
rust-development
Idiomatisk Rust-utvikling med cargo, clippy, error handling, async/tokio, unsafe og testing.
cargo-fuzz
Use when initializing, running, measuring coverage, or triaging a cargo-fuzz target in a Rust crate. Not for remote, credential, publish, deploy, or irreversible changes.