mcp-picnic: Command for Claude Code

.claude/commands/minispec.tasks.md

minispec.tasks is a command for Claude Code from ivo-toby/mcp-picnic. It costs 16 tokens per session (2,317 once invoked), scanned A, original, MIT.

An interactive command that turns a software design into small, reviewable implementation tasks for pair programming.

In plain words
What is it for?
Use it to plan implementation tasks from a design, check prerequisites, identify dependencies, and size work according to a project's review preferences.
Why use it?
Large designs can be difficult to implement and review as one change. Breaking them into ordered chunks clarifies dependencies and parallel work.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is ivo-toby/mcp-picnic's own configuration. It tells Claude Code how to work on mcp-picnic 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-picnic configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ivo-toby/mcp-picnic. 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/ivo-toby/mcp-picnic/main/.claude/commands/minispec.tasks.md
Clone the repo
git clone --depth 1 https://github.com/ivo-toby/mcp-picnic

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 minispec.tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.tasks/github.svg)](https://agentmods.dev/commands/ivo-toby/mcp-picnic/minispec.tasks)
Your own site
<a href="https://agentmods.dev/commands/ivo-toby/mcp-picnic/minispec.tasks"><img src="https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.tasks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for minispec.tasks

Your own site · 80×15
<a href="https://agentmods.dev/commands/ivo-toby/mcp-picnic/minispec.tasks"><img src="https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,317 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 $0.00016 $0.02317
Opus 5 $0.00008 $0.01158
Sonnet 5 $0.00003 $0.00463
Haiku 4.5 $0.00002 $0.00232

Measured 10d ago against content hash 03c5c3c72791, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minispec.tasks 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 10d 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.

.claude/commands/minispec.tasks.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You are helping break down a design into implementable tasks through conversation. Tasks should be sized according to the engineer's review chunk preference from the constitution.

Philosophy

Task breakdown is not just about creating a list—it's about:

  • Understanding the implementation sequence
  • Identifying dependencies and parallelization opportunities
  • Sizing chunks for comfortable review
  • Ensuring the engineer understands what each task involves

Prerequisites

Before starting, verify:

  1. Constitution exists at .minispec.minispec/memory/constitution.md

    • Read the Review Chunk Size preference (small/medium/large/adaptive)
    • This determines target lines per task
  2. Design exists - Look for:

    • .minispec/specs/[feature-name]/design.md
    • If $ARGUMENTS specifies a feature, use that
    • If not, check for recent designs or ask which feature

If no design exists:

"I don't see a design for this feature yet. Want to run /minispec.design first, or give me a quick overview of what we're building?"

Chunk Size Guidelines

Based on constitution preference:

Preference Target Lines Typical Scope
Small 20-40 lines Single function, one test
Medium 40-80 lines Related functions, model + migration
Large 80-150 lines Full component, endpoint + tests
Adaptive Varies AI suggests based on complexity

Execution Flow

Phase 0: Set Up Tasks File

IMPORTANT: Before doing anything else, run the setup script to prepare the tasks file.

Run this command:

.minispec/scripts/bash/setup-plan.sh --json

This will:

  • Ensure the feature spec directory exists
  • Copy the tasks template to tasks.md
  • Output paths for DESIGN, TASKS, FEATURE_DIR, and BRANCH

Parse the JSON output to locate the design and tasks files. If the script fails, create the tasks file manually at .minispec/specs/[feature-name]/tasks.md.

Read the full file on GitHub · 317 lines

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. 10d ago First seen · 317 lines · 16 tokens per session scan A 03c5c3c72791

Subscribe to this mod's changes

minispec.tasks is a command published in the GitHub repository ivo-toby/mcp-picnic (98 stars, last pushed 26d ago), licensed MIT. It adds 16 tokens to every session and 2,317 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 2026-08-30.