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/cli-reviewgit clone --depth 1 https://github.com/geoffjay/claude-pluginsWhat 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 | $0.00019 | $0.02578 |
| Opus 5 | $0.00010 | $0.01289 |
| Sonnet 5 | $0.00004 | $0.00516 |
| Haiku 4.5 | $0.00002 | $0.00258 |
Grade A, and why
cli-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 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.
How it starts
The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Review Command
Comprehensively review a Rust CLI application for code quality, user experience, error handling, testing coverage, and cross-platform compatibility.
Arguments
$1- Path to project directory (optional, defaults to current directory)--focus- Specific area to focus on: "ux", "errors", "tests", "config", "perf", or "all" (optional, default: "all")
Usage
# Review current directory
/cli-review
# Review specific project
/cli-review /path/to/my-cli
# Focus on specific area
/cli-review --focus ux
/cli-review --focus errors
/cli-review --focus tests
Review Areas
1. Argument Design & CLI Interface
Checks:
- Argument naming follows conventions (kebab-case)
- Short and long forms provided where appropriate
- Help text is clear and descriptive
- Defaults are sensible and documented
- Mutually exclusive args use proper groups
- Required args are clearly marked
- Value names are descriptive (FILE, PORT, URL)
- Global options work with all subcommands
- Version information is present
Example Issues:
❌ Issue: Unclear argument name
File: src/cli.rs:15
Found: #[arg(short, long)]
pub x: String,
Recommendation: Use descriptive names
#[arg(short, long, value_name = "FILE")]
pub input_file: PathBuf,
2. Help Text Quality
Checks:
- Command-level help is present
- All arguments have descriptions
- Long help provides examples
- Help text uses active voice
- Complex options have detailed explanations
- Examples section shows common usage
- After-help provides additional resources
Example Issues:
❌ Issue: Missing help text
File: src/cli.rs:23
Found: #[arg(short, long)]
pub verbose: bool,
Recommendation: Add descriptive help
/// Enable verbose output with detailed logging
#[arg(short, long)]
pub verbose: bool,
3. Error Messages
Checks:
- Errors explain what went wrong
- Errors suggest how to fix the problem
- File paths are displayed in error messages
- Using miette or similar for rich diagnostics
- Error types are well-structured (thiserror)
- Context is added at each error level
- Exit codes are meaningful and documented
- Errors go to stderr, not stdout
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 · 448 lines · 19 tokens per session scan A 60b7b406ae2d
cli-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 2,578 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.