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/paulbreuler/limps/create-feature-plangit clone --depth 1 https://github.com/paulbreuler/limpsWhat 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 | $0.00000 | $0.03291 |
| Opus 5 | $0.00000 | $0.01646 |
| Sonnet 5 | $0.00000 | $0.00658 |
| Haiku 4.5 | $0.00000 | $0.00329 |
Grade A, and why
create-feature-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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Feature Plan v2.1.0
Generate a TDD plan with verbose planning docs and minimal agent execution files using MCP planning tools.
LLM Execution Rules
- Use MCP planning tools for all reads/writes; do not write files directly.
- Do not include secrets, tokens, or credentials in plan content.
- Only run
process_doc/process_docswith code you authored or reviewed.
Invocation
/create-feature-plan
MCP Integration
This command uses limps MCP tools for document management:
- Server:
limps - Tools:
create_plan- Create the plan structurecreate_doc- Create planning documents ({plan-name}-plan.md, interfaces.md, README.md, gotchas.md)list_docs- List existing plans to determine next plan numberprocess_doc- Process documents with JavaScript (read, filter, transform, extract)process_docs- Process multiple documents with JavaScript (analyze patterns across plans)search_docs- Full-text search across documents
Usage: Call tools via call_mcp_tool with server: "limps" and the tool name (e.g., create_plan, create_doc, etc.)
Plan Operations Skill
Use /limps-plan-operations to keep plan identification and artifact loading consistent:
identify-planwhen referencing an existing plan for comparison or migration contextresolve-pathto normalize plan names/paths before constructing doc pathsload-artifactsto read plan files, interfaces, README, gotchas, and agents via MCP tools
Workflow
Phase 1: Gather Context
Ask user for:
- Project name and scope
- Work type:
refactor|overhaul|features - Tech stack and existing patterns
- Prototype/reference documents
- Known gotchas upfront
Phase 2: Create Planning Docs (Verbose)
Use MCP tools for document creation:
- Create plan structure using
create_plan(server:limps):- Plan name:
descriptive-name(NO numeric prefix) create_planprefixes the next plan number automatically (e.g.,0043-descriptive-name)- If you already have an
NNNN-prefix, strip it to avoid duplication - Description: Brief overview of the plan
- Plan name:
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 · 464 lines · 0 tokens per session scan A 5b4f78f04d13
create-feature-plan is a command published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,291 tokens. 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
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
go-test
Go TDD workflow with table-driven tests.
pm-auto-design2dev
設計レビューから実装完了まで完全自動化（設計レビュー→作業計画→TDD実装）.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.
tdd
强制执行测试驱动开发工作流。首先搭建接口，生成测试，然后从实现能通过测试的最小代码。确保 80%+ 的覆盖率。.