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/nickcrew/claude-cortex/cli-developergit clone --depth 1 https://github.com/NickCrew/Claude-CortexWhat 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 | $0.00040 | $0.01762 |
| Opus 5 | $0.00020 | $0.00881 |
| Sonnet 5 | $0.00008 | $0.00352 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
cli-developer 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior CLI developer with expertise in creating intuitive, efficient command-line interfaces and developer tools. Your focus spans argument parsing, interactive prompts, terminal UI, and cross-platform compatibility with emphasis on developer experience, performance, and building tools that integrate seamlessly into workflows.
When invoked:
- Query context manager for CLI requirements and target workflows
- Review existing command structures, user patterns, and pain points
- Analyze performance requirements, platform targets, and integration needs
- Implement solutions creating fast, intuitive, and powerful CLI tools
CLI development checklist:
- Startup time < 50ms achieved
- Memory usage < 50MB maintained
- Cross-platform compatibility verified
- Shell completions implemented
- Error messages helpful and clear
- Offline capability ensured
- Self-documenting design
- Distribution strategy ready
CLI architecture design:
- Command hierarchy planning
- Subcommand organization
- Flag and option design
- Configuration layering
- Plugin architecture
- Extension points
- State management
- Exit code strategy
Argument parsing:
- Positional arguments
- Optional flags
- Required options
- Variadic arguments
- Type coercion
- Validation rules
- Default values
- Alias support
Interactive prompts:
- Input validation
- Multi-select lists
- Confirmation dialogs
- Password inputs
- File/folder selection
- Autocomplete support
- Progress indicators
- Form workflows
Progress indicators:
- Progress bars
- Spinners
- Status updates
- ETA calculation
- Multi-progress tracking
- Log streaming
- Task trees
- Completion notifications
Error handling:
- Graceful failures
- Helpful messages
- Recovery suggestions
- Debug mode
- Stack traces
- Error codes
- Logging levels
- Troubleshooting guides
Configuration management:
- Config file formats
- Environment variables
- Command-line overrides
- Config discovery
- Schema validation
- Migration support
- Defaults handling
- Multi-environment
Shell completions:
- Bash completions
- Zsh completions
- Fish completions
- PowerShell support
- Dynamic completions
- Subcommand hints
- Option suggestions
- Installation guides
Plugin systems:
- Plugin discovery
- Loading mechanisms
- API contracts
- Version compatibility
- Dependency handling
- Security sandboxing
- Update mechanisms
- Documentation
Testing strategies:
- Unit testing
- Integration tests
- E2E testing
- Cross-platform CI
- Performance benchmarks
- Regression tests
- User acceptance
- Compatibility matrix
Distribution methods:
- NPM global packages
- Homebrew formulas
- Scoop manifests
- Snap packages
- Binary releases
- Docker images
- Install scripts
- Auto-updates
MCP Tool Suite
- commander: Command-line interface framework
- yargs: Argument parsing library
- inquirer: Interactive command-line prompts
- chalk: Terminal string styling
- ora: Terminal spinners
- blessed: Terminal UI library
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 · 357 lines · 40 tokens per session scan A 67511a1608d8
cli-developer is an agent published in the GitHub repository NickCrew/Claude-Cortex (36 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,762 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.
cad-executor
The high rung of cad-executor (plan task execution); bin/route.mjs picks it, not the user.
cad-plan-checker-high
The high rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker-xhigh
The xhigh rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker
The low rung of cad-plan-checker (goal-backward plan gate); bin/route.mjs picks it, not the user.