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 commands/geoffjay/claude-plugins/tokio-reviewgit clone --depth 1 https://github.com/geoffjay/claude-pluginsWrote 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/commands/geoffjay/claude-plugins/tokio-review)<a href="https://agentmods.dev/commands/geoffjay/claude-plugins/tokio-review"><img src="https://agentmods.dev/badge/commands/geoffjay/claude-plugins/tokio-review.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 | $0.00019 | $0.01599 |
| Opus 5 | $0.00010 | $0.00800 |
| Sonnet 5 | $0.00004 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
tokio-review 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 6d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokio Review Command
This command performs comprehensive code review of Tokio-based applications, identifying async/await anti-patterns, performance issues, blocking operations, and suggesting improvements.
Arguments
$1- File path or directory to review (optional, defaults to current directory)
Usage
/rust-tokio-expert:tokio-review
/rust-tokio-expert:tokio-review src/handlers/
/rust-tokio-expert:tokio-review src/main.rs
Workflow
-
Analyze Target
- If no argument provided, scan current directory for Rust files
- If directory provided, scan all
.rsfiles recursively - If file provided, review that specific file
-
Read Relevant Files
- Use Glob tool to find Rust source files
- Read all identified files using Read tool
- Prioritize files in: src/main.rs, src/lib.rs, src/**/*.rs
-
Invoke Agent
- Use Task tool with
subagent_type="rust-tokio-expert:tokio-performance" - Provide all source code context to the agent
- Request comprehensive analysis
- Use Task tool with
-
Review Checklist
The agent should analyze for:
Async/Await Anti-Patterns
-
Blocking Operations in Async Context
- Detect
std::thread::sleepinstead oftokio::time::sleep - Identify blocking I/O operations
- Find CPU-intensive operations not wrapped in
spawn_blocking
- Detect
-
Holding Locks Across Await Points
- Detect
std::sync::Mutexortokio::sync::Mutexheld across.await - Suggest lock scope reduction
- Recommend alternatives like channels
- Detect
-
Unnecessary Cloning
- Identify expensive clones in async contexts
- Suggest
Arcfor shared data - Recommend reference passing where possible
-
Futures Not Being Awaited
- Find async functions called without
.await - Detect unused futures
- Identify missing error handling
- Find async functions called without
Performance Issues
- Excessive Task Spawning
- Detect unbounded task creation in loops
- Suggest
buffer_unorderedor bounded concurrency - Recommend semaphore-based limiting
-
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.
- 6d ago First seen · 249 lines · 19 tokens per session scan A 76e014fadbb6
tokio-review is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 1,599 once invoked, about $0.0001 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 commands, from other repositories
new-op
Guide for adding a new variant to the Op enum (e.g. Op::Tag, Op::Link). Covers every place that needs to change.
cargo-metadata
Command "cargo-metadata" from olorehq/olore, covering cargo-metadata(1), name, synopsis, description and output format.
cargo-bench
Command "cargo-bench" from olorehq/olore, covering cargo-bench(1), name, synopsis, description and working directory of benchmarks.
cargo-build
Command "cargo-build" from olorehq/olore, covering cargo-build(1), name, synopsis, description and options.
cargo-check
Command "cargo-check" from olorehq/olore, covering cargo-check(1), name, synopsis, description and options.
add
Command "add" from paiml/rust-mcp-sdk, covering cargo pmcp add, usage, subcommands, add server and arguments.