mcp-swiss: Command for Claude Code

.specify/commands/speckit.plan.md

speckit.plan is a command for Claude Code from vikramgorla/mcp-swiss. It costs 0 tokens per session (468 once invoked), scanned A, original, MIT.

A command that reads a feature specification and creates an architectural implementation plan in the same folder. The plan covers design, data flow, module structure, edge cases, and error handling.

In plain words
What is it for?
Use it with a specification ID to create a plan.md file for a feature or module.
Why use it?
It turns a written requirement into a consistent technical outline before coding begins.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

This is vikramgorla/mcp-swiss's own configuration. It tells Claude Code how to work on mcp-swiss itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-swiss configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vikramgorla/mcp-swiss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vikramgorla/mcp-swiss/main/.specify/commands/speckit.plan.md
Clone the repo
git clone --depth 1 https://github.com/vikramgorla/mcp-swiss

Made for: Claude Code.

Wrote 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.

agentmods badge for speckit.plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/vikramgorla/mcp-swiss/speckit.plan.svg)](https://agentmods.dev/commands/vikramgorla/mcp-swiss/speckit.plan)
Your own site
<a href="https://agentmods.dev/commands/vikramgorla/mcp-swiss/speckit.plan"><img src="https://agentmods.dev/badge/commands/vikramgorla/mcp-swiss/speckit.plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00468
Opus 5 $0.00000 $0.00234
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured 7d ago against content hash bee3aea618e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

speckit.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 7d 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.

.specify/commands/speckit.plan.md · 77 lines

What it actually says

Speckit Command: /plan

Command: /plan <spec-id>
Purpose: Generate an architectural plan from a spec. Reads specs/<NNN>-*/spec.md and creates plan.md.


Instructions for AI

When the user runs /plan <spec-id> (e.g. /plan 005), read the corresponding specs/0<spec-id>-*/spec.md and generate a plan.md in the same directory.

Plan Template

# Plan: <Feature Name>

**Spec:** <NNN>
**Status:** Draft | In Progress | Implemented ✅

---

## Architectural Vision

<2-4 sentences describing the overall approach. What pattern is used? Why?>

## Data Flow

\```
<ASCII diagram showing the data flow from MCP tool call → implementation → API → response>
\```

## Key Design Decisions

1. **<decision title>:** <rationale>
2. **<decision title>:** <rationale>

## Module Structure

\```
src/modules/<name>.ts
├── <ToolName>Tools: array    — MCP tool definitions
└── handle<Name>(name, args)  — tool call dispatcher
\```

## Edge Cases

| Case | Handling |
|------|----------|
| <edge case> | <how handled> |

## Error Handling

| Scenario | HTTP Status | Handling |
|---------|-------------|----------|
| <scenario> | <status> | <handling> |

## Performance Notes

- <performance characteristic>
- <caching approach if any>
- <timeout considerations>

## Security & Privacy

- <note on data handling>
- <auth requirements if any>

Rules

  1. Plan must match the spec — every P0 tool in spec.md must be covered in the plan
  2. Data flow diagram must be ASCII art — no images
  3. Edge cases must include: not-found, API error, missing required params
  4. If using a new HTTP pattern (POST body, path params, etc), document it explicitly
  5. Flag any dependencies on other modules or external systems
  6. Note coordinate system quirks (WGS84 vs LV95 for geodata)
Changes

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.

  1. 7d ago First seen · 77 lines · 0 tokens per session scan A bee3aea618e9

Subscribe to this mod's changes

speckit.plan is a command published in the GitHub repository vikramgorla/mcp-swiss (22 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 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 2026-08-30.