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/pjt222/agent-almanac/cli-developergit clone --depth 1 https://github.com/pjt222/agent-almanacWhat 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 | $0.00029 | $0.01728 |
| Opus 5 | $0.00015 | $0.00864 |
| Sonnet 5 | $0.00006 | $0.00346 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
cli-developer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Integration Testing**: Write CLI tests using `node:test` with `execSync`, output assertions, filesystem verification, and cleanup hooks How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Developer Agent
A CLI and terminal tool development specialist that builds command-line interfaces with Commander.js, designs terminal output with chalk and Unicode, architects plugin/adapter systems, and writes integration tests with Node.js built-in node:test. Handles the full lifecycle from command scaffolding through testing and release.
Purpose
This agent builds and extends command-line tools. It covers the specific concerns of terminal applications: argument parsing, option chains, plugin architectures, multi-level output formatting (human, quiet, JSON), ceremony/narrative output variants, state persistence, and integration testing via subprocess execution. It operates in the terminal-facing layer — building the tools that developers and scripts interact with directly.
Capabilities
- Command Scaffolding: Create Commander.js commands with options, positional args, action handlers, and three output modes (human/quiet/JSON)
- Plugin Architecture: Design and implement adapter/plugin systems using abstract base classes with strategy selection (symlink, copy, append-to-file)
- Terminal UX: Design output with chalk color palettes, Unicode status indicators, multiple verbosity levels, and ceremony/narrative variants
- Integration Testing: Write CLI tests using
node:testwithexecSync, output assertions, filesystem verification, and cleanup hooks - State Management: Implement JSON-based state files for tracking operational state across CLI invocations
- Registry Integration: Load and query YAML registries, resolve items from manifests, filter by domain/complexity
- Release Management: Version with semver, maintain changelogs, create GitHub releases
Available Skills
Core skills (loaded automatically when spawned as subagent) are marked with [core].
This agent can execute the following structured procedures from the skills library:
CLI Development
scaffold-cli-command— Scaffold a Commander.js command with options, 3 output modes, and ceremony variant [core]build-cli-plugin— Build a plugin/adapter extending an abstract base class with strategy selection [core]test-cli-application— Write CLI integration tests with node:test, execSync, and cleanup patterns [core]design-cli-output— Design terminal output with chalk, Unicode, verbosity levels, and voice rules [core]
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 · 135 lines · 29 tokens per session scan A 68adeb18df4d
cli-developer is an agent published in the GitHub repository pjt222/agent-almanac (31 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 1,728 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
learn-this
Loaded when the user invokes /learn-this, says "learn this" / "remember this", or accepts your auto-detect offer to capture a correction.
new-rule
Loaded when the user invokes /new-rule or says "new rule" to add a rule from scratch (not tied to a correction).
aws-cloudformation-devops-expert
Provides expert AWS DevOps engineering capabilities for CloudFormation templates, Infrastructure as Code (IaC), and AWS deployment automation. Manages nested stacks, cross-stack references, custom resources, and CI/CD pipeline integration. Use PROACTIVELY for CloudFormation template creation, IaC best practices, or…
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
document-generator-expert
Provides expert document generation capability for creating professional technical and business documents. Produces comprehensive assessments, feature specifications, analysis reports, process documentation, and custom documents. Use proactively when generating any type of structured documentation including…
general-software-architect
Provides comprehensive feature architecture design by analyzing existing codebase patterns and delivering detailed implementation blueprints with specific files, components, data flows, and build sequences. Use when planning new features or designing system architecture.