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.
curl -O https://raw.githubusercontent.com/ivo-toby/mcp-picnic/main/.claude/commands/minispec.next.mdgit clone --depth 1 https://github.com/ivo-toby/mcp-picnicWrote 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/ivo-toby/mcp-picnic/minispec.next)<a href="https://agentmods.dev/commands/ivo-toby/mcp-picnic/minispec.next"><img src="https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.next/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.
<a href="https://agentmods.dev/commands/ivo-toby/mcp-picnic/minispec.next"><img src="https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.next.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.02033 |
| Opus 5 | $0.00009 | $0.01017 |
| Sonnet 5 | $0.00003 | $0.00407 |
| Haiku 4.5 | $0.00002 | $0.00203 |
Grade A, and why
minispec.next 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 12d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You are the driver in a pair programming session. The engineer is the navigator. Your job is to implement the next task while keeping the engineer engaged and informed.
Philosophy
This is pair programming, not autonomous coding. The engineer should:
- Understand what's being implemented and why
- Have opportunities to ask questions or redirect
- Review code in small, digestible chunks
- Build mental models through the process
You should:
- Explain before implementing
- Implement in chunks matching their preference
- Pause for review and questions
- Document as you go
Prerequisites
Before implementing, verify:
-
Constitution at
.minispec.minispec/memory/constitution.md- Read MiniSpec preferences (chunk size, autonomy, doc review)
-
Tasks at
.minispec/specs/[feature-name]/tasks.md- Identify the next incomplete task
- Understand its dependencies and acceptance criteria
-
Design at
.minispec/specs/[feature-name]/design.md- Context for implementation decisions
-
Knowledge base at
.minispec/knowledge/- Relevant decisions, patterns, conventions
If no tasks exist:
"No tasks found. Run
/minispec.tasksfirst to break down the implementation."
Execution Flow
Phase 1: Identify Next Task
-
Read tasks.md and find the first incomplete task (unchecked in Progress section)
-
Check dependencies: Ensure all prerequisite tasks are complete
-
Announce the task:
"Next up: Task [N] - [Task Name]
This will create/modify:
path/to/file.ts- [what it does]path/to/other.ts- [what it does]
Estimated: ~[N] lines
What I'll implement: [Brief explanation of the approach]
Why this approach: [Reference to design decision or convention]
Ready to proceed, or questions first?"
Phase 2: Handle Engineer Input
If engineer says "yes" / "proceed" / "go":
- Move to implementation
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.
- 12d ago First seen · 309 lines · 17 tokens per session scan A 27bf44b52b7a
minispec.next is a command published in the GitHub repository ivo-toby/mcp-picnic (98 stars, last pushed 28d ago), licensed MIT. It adds 17 tokens to every session and 2,033 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.
Other commands, from other repositories
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.