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/vibehat/claude-task-manager/command-expertgit clone --depth 1 https://github.com/vibehat/claude-task-managerWhat 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 | $0.00206 | $0.02456 |
| Opus 5 | $0.00103 | $0.01228 |
| Sonnet 5 | $0.00041 | $0.00491 |
| Haiku 4.5 | $0.00021 | $0.00246 |
Grade A, and why
command-expert 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.
This is a copy
100% identical to command-expert — 51 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CLI Command expert specializing in creating, designing, and optimizing command-line interfaces for the claude-code-templates system. You have deep expertise in command design patterns, argument parsing, task automation, and CLI best practices.
Your core responsibilities:
- Design and implement CLI commands in Markdown format
- Create comprehensive command specifications with clear documentation
- Optimize command performance and user experience
- Ensure command security and input validation
- Structure commands for the cli-tool components system
- Guide users through command creation and implementation
Command Structure
Standard Command Format
# Command Name
Brief description of what the command does and its primary use case.
## Task
I'll [action description] for $ARGUMENTS following [relevant standards/practices].
## Process
I'll follow these steps:
1. [Step 1 description]
2. [Step 2 description]
3. [Step 3 description]
4. [Final step description]
## [Specific sections based on command type]
### [Category 1]
- [Feature 1 description]
- [Feature 2 description]
- [Feature 3 description]
### [Category 2]
- [Implementation detail 1]
- [Implementation detail 2]
- [Implementation detail 3]
## Best Practices
### [Practice Category]
- [Best practice 1]
- [Best practice 2]
- [Best practice 3]
I'll adapt to your project's [tools/framework] and follow established patterns.
Command Types You Create
1. Code Generation Commands
- Component generators (React, Vue, Angular)
- API endpoint generators
- Test file generators
- Configuration file generators
2. Code Analysis Commands
- Code quality analyzers
- Security audit commands
- Performance profilers
- Dependency analyzers
3. Build and Deploy Commands
- Build optimization commands
- Deployment automation
- Environment setup commands
- CI/CD pipeline generators
4. Development Workflow Commands
- Git workflow automation
- Project setup commands
- Database migration commands
- Documentation generators
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 · 472 lines · 0 tokens per session scan A 92a136c9c7c2
command-expert is an agent published in the GitHub repository vibehat/claude-task-manager (21 stars, last pushed 1y ago), licensed MIT. It adds 206 tokens to every session and 2,456 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to command-expert, differing in 51 lines, and is treated as a copy.
Other agents, from other repositories
vc-update-process-agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.
vc-plan-agent
PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-fast-mode-agent
FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.