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/kensaurus/cursor-kenji/plangit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWhat 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 | $0.00503 |
| Opus 5 | $0.00010 | $0.00251 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
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 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Before Coding
Purpose
Use Plan Mode to research, clarify requirements, and produce an approved implementation plan before writing a single line of code.
Runtime note:
Shift+Tabtoggles plan mode in both Cursor and Claude Code. The "Save to workspace →.cursor/plans/" step and the mode-selector dropdown are Cursor-specific. In Claude Code, approve the plan through the plan-mode prompt (ExitPlanMode); there is no.cursor/plans/file.
Process
1. Activate Plan Mode
Press Shift+Tab in the agent input to toggle Plan Mode, or use the mode selector dropdown.
The agent will:
- Search the codebase for relevant files and context
- Ask clarifying questions about requirements
- Produce a detailed plan with file paths and code references
- Wait for approval before building
2. Review & Refine the Plan
Plans open as Markdown. Edit directly to:
- Remove unnecessary steps
- Adjust the approach or architecture
- Add context the agent missed
- Specify patterns, libraries, or constraints
Save to workspace: Click "Save to workspace" → stored at .cursor/plans/. Useful for:
- Team documentation
- Resuming interrupted work
- Context for future agents on the same feature
3. Approve & Execute
Once the plan looks right, approve it. The agent switches to implementation mode.
If the result doesn't match expectations:
- Revert the changes
- Refine the plan with more specifics
- Re-run — faster than fixing a wrong implementation
4. Checklist
- Requirements clearly stated
- Existing patterns identified (check codebase first)
- Affected files listed
- Edge cases noted
- Plan saved to
.cursor/plans/if significant - Plan approved before implementation starts
When to Use
- New features touching multiple files
- Architectural decisions
- Unfamiliar areas of the codebase
- Any task where the wrong direction wastes significant time
When to Skip
- Small, isolated changes you've done many times
- Bug fixes with an obvious root cause
- Single-file edits with clear requirements
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 · 66 lines · 19 tokens per session scan A 733c71c4627d
plan is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 503 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
commit-msg
Cursor tooling: skills, rules, subagents.
boot
Initialize agent, verify setup, and load rules.
code-review
Confidence-based code review checklist.
prp-new
Create new Product Requirement Prompt from scratch.
clean
Repository hygiene — clean temp files, organize execution folders.
context
Dynamic context management — status, clean, log, save, read.