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 skills add opsmill/infrahub-mcp --skill speckit-tinyspec-classifygit clone --depth 1 https://github.com/opsmill/infrahub-mcpWrote 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/skills/opsmill/infrahub-mcp/speckit-tinyspec-classify)<a href="https://agentmods.dev/skills/opsmill/infrahub-mcp/speckit-tinyspec-classify"><img src="https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-tinyspec-classify/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/skills/opsmill/infrahub-mcp/speckit-tinyspec-classify"><img src="https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-tinyspec-classify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00951 |
| Opus 5 | $0.00012 | $0.00476 |
| Sonnet 5 | $0.00005 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
speckit-tinyspec-classify 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classify Task Complexity
Analyze a task description to determine whether it should use the lightweight tinyspec workflow or the full SDD workflow (specify → plan → tasks → implement). Acts as an intelligent router that saves time on small tasks and ensures proper process for complex ones.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty). The user describes what they want to build or fix.
Prerequisites
- Verify a spec-kit project exists by checking for
.specify/directory - Verify the user has described the task (if not, ask what they want to build)
Outline
-
Analyze the task: Evaluate the task description against complexity signals:
Small task signals (→ tinyspec):
Signal Example Single UI component change "Add a logout button" Bug fix with known location "Fix date format in invoices" Config or environment change "Add new env variable for API key" Simple validation addition "Add email validation to signup" Copy/text update "Update error messages" Single endpoint addition "Add GET /health endpoint" Styling change "Make the sidebar responsive" Large task signals (→ full SDD):
Signal Example Multiple modules affected "Add user authentication system" New database tables/schema "Add a comments feature with threading" Architectural change "Migrate from REST to GraphQL" New service or integration "Add Stripe payment processing" Cross-cutting concern "Add audit logging to all endpoints" Multiple user stories "Build the admin dashboard" Unknown scope "Improve performance" (needs investigation first) -
Estimate scope: Quick estimation based on available information:
- Files affected: How many files will likely change
- Task count: How many distinct implementation steps
- Risk level: How likely is this to break existing functionality
- Dependencies: Does this require coordination across modules
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.
- 6d ago First seen · 95 lines · 24 tokens per session scan A 56e41abf9aba
speckit-tinyspec-classify is a skill published in the GitHub repository opsmill/infrahub-mcp (10 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 951 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 2026-09-03.
Other skills, from other repositories
tensorpool-gpu-cloud
Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.
lambda-gpu-cloud
Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions.
runpod-gpu-cloud
Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.
vast-ai-gpu-cloud
Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.
givemeanode-agent-compute
Operate GiveMeANode GPU nodes, batch jobs, storage, and rollout sandboxes through its connected MCP server with bounded spend, durable recovery, and explicit approval for paid or destructive actions.
gpt-image-gen
MUST read before generating images. Detailed prompt-crafting guide for gpt-image models, covering tool routing (native imagegeneration server tool vs the generateimage tool), prompt structure from subject to background, verbatim text rendering, anti-patterns, and the revisedprompt feedback loop for iteration.