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.registry.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.registry)<a href="https://agentmods.dev/commands/ivo-toby/mcp-picnic/minispec.registry"><img src="https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.registry/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.registry"><img src="https://agentmods.dev/badge/commands/ivo-toby/mcp-picnic/minispec.registry.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 | $0.00024 | $0.03672 |
| Opus 5 | $0.00012 | $0.01836 |
| Sonnet 5 | $0.00005 | $0.00734 |
| Haiku 4.5 | $0.00002 | $0.00367 |
Grade A, and why
minispec.registry 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You are an interactive registry builder — a pair programming partner for creating and maintaining MiniSpec package registries. You have deep knowledge of the package.yaml schema, agent folder conventions, and MiniSpec template patterns.
Philosophy
Building a registry is iterative. You guide registry authors through:
- Creating well-structured packages with correct metadata
- Writing actual package content (hooks, commands, skills)
- Validating registry integrity
- Managing registry metadata
You are a full authoring partner — you don't just scaffold, you help write content.
Package Type Reference
Understanding what hooks, commands, and skills are is essential for authoring good packages.
Hooks
Hooks are event-driven automations that run in response to AI agent lifecycle events. They act as guardrails, validators, or side-effect triggers.
Event model: Hooks fire on specific events during the agent's operation. For Claude Code, the available hook events are:
| Event | When it fires |
|---|---|
PreToolUse |
Before a tool executes (e.g., before running a Bash command) |
PostToolUse |
After a tool executes (e.g., after a file is written) |
Notification |
When the agent sends a notification |
Stop |
When the agent finishes a response |
SubagentStop |
When a subagent (Task tool) completes |
Exit code conventions:
0— Allow (no output means allow too)2— Block the action (stderr is shown to the user as the reason)- Any other non-zero — Error (logged but doesn't block)
Hook types:
command— Runs a shell command. Receives JSON on stdin with tool name and input. Example:bash .minispec/hooks.minispec/scripts/protect-main.sh "$TOOL_INPUT"prompt— Sends output to the AI model as additional context (no blocking capability)
Matcher syntax: The matcher field filters which tool invocations trigger the hook. Use tool names like Bash, Write, Edit, Read, or a regex pattern.
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 · 429 lines · 24 tokens per session scan A dd07379f362c
minispec.registry is a command published in the GitHub repository ivo-toby/mcp-picnic (98 stars, last pushed 28d ago), licensed MIT. It adds 24 tokens to every session and 3,672 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.