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/benshapyro/cadre-devkit-claude/plangit clone --depth 1 https://github.com/benshapyro/cadre-devkit-claudeWrote 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/benshapyro/cadre-devkit-claude/plan)<a href="https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/plan"><img src="https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/plan.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 | $0.00007 | $0.01503 |
| Opus 5 | $0.00003 | $0.00751 |
| Sonnet 5 | $0.00001 | $0.00301 |
| Haiku 4.5 | $0.00001 | $0.00150 |
Grade A, and why
plan 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 4d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Command
Plan a new feature or task with proper structure before implementation.
Reference skills based on feature type:
- API/backend: Read
.claude/skills/api-design-patterns/SKILL.md - React components: Read
.claude/skills/react-patterns/SKILL.md - UI styling: Read
.claude/skills/tailwind-conventions/SKILL.md - Error handling: Read
.claude/skills/error-handler/SKILL.md - TDD mode: Read
.claude/skills/test-generator/SKILL.md
For new projects: Use /greenfield first to define specs, then /plan for implementation.
Flags
--tdd- Enable Test-Driven Development mode (write tests first)
Validation
If no feature description provided, ask for one.
Planning Steps
1. Gather Context (REQUIRED)
You MUST read relevant files before creating a plan. Don't plan based on assumptions.
Before planning:
- Read relevant CLAUDE.md files
- Read the actual files that will be modified
- Identify existing patterns and conventions
- Understand related code and dependencies
Use Explore agent or direct file reads to understand:
- Current implementation
- Existing patterns in similar code
- Test file locations and patterns
2. Requirements Clarification
Ask clarifying questions if needed:
- What is the expected behavior?
- What are the edge cases?
- What are the acceptance criteria?
- Are there performance requirements?
3. Create Plan
Structure the implementation with specific details:
Detail Level Guidelines:
| Change Type | Detail Level |
|---|---|
| Complex/risky changes | Line numbers + code snippets |
| Medium changes | Function/method names |
| Simple/obvious changes | File paths only |
| New files | File path + structure outline |
Output Format:
## Feature: [description]
### Requirements
- [ ] Requirement 1
- [ ] Requirement 2
### Technical Approach
1. Step 1 - [description]
- Why: [reasoning for this approach]
2. Step 2 - [description]
### Files to Modify
#### `path/to/file.ts` (lines 45-67)
**Current:** [brief description of current state]
**Change:** [what will change]
```typescript
// Example of the change (for complex modifications)
function existingFunction() {
// Add: new caching logic here
}
path/to/new-file.ts (NEW)
Purpose: [why this file is needed] Structure:
functionA()- [purpose]functionB()- [purpose]
Dependencies
- [list any new dependencies]
Testing Strategy
- Unit tests: [specific test cases]
- Integration tests: [approach]
- Test file:
path/to/tests/file.test.ts
Alternatives Considered
- [Alternative 1] - [why not chosen]
Risks
- [potential issue] - [mitigation]
Complexity
- [low/medium/high] - [justification]
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.
- 4d ago First seen · 246 lines · 0 tokens per session scan A 148928498f4f
plan is a command published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 7 tokens to every session and 1,503 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
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.