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-auto-rungit 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-auto-run)<a href="https://agentmods.dev/skills/opsmill/infrahub-mcp/speckit-auto-run"><img src="https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-auto-run/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-auto-run"><img src="https://agentmods.dev/badge/skills/opsmill/infrahub-mcp/speckit-auto-run.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 | $0.00037 | $0.00911 |
| Opus 5 | $0.00018 | $0.00456 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
speckit-auto-run 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
You are running the full speckit pipeline end-to-end. The user's input (above) is the feature description that will seed the specification phase.
Execute every phase below in order, making all decisions autonomously. Do not stop to ask the user for input between phases — if a phase requires choices (e.g., clarification questions in specify, research decisions in plan), use your best judgment and proceed. The user expects a hands-off, one-shot execution.
After each phase, invoke the speckit-checkpoint-commit skill to commit the artifacts produced by that phase before moving on.
Each phase below is executed by invoking the named skill (e.g. via the agent's Skill tool). Skills are agent-agnostic, so this workflow runs identically across any harness that supports skill discovery — not only those exposing speckit slash commands.
Phase 1 — Specify
Invoke the speckit-specify skill with the user's feature description ($ARGUMENTS).
- Complete the full specify workflow: generate a short name, create the spec directory, write
spec.md, run quality checks. - If clarification questions arise, answer them yourself based on context and best judgment — do not pause for user input.
- Commit the spec artifacts.
Phase 2 — Plan
Invoke the speckit-plan skill.
- Complete the full plan workflow: research unknowns, generate
plan.md,research.md,data-model.md, API contracts,quickstart.md. - Make all design decisions autonomously.
- Commit the plan artifacts.
Phase 3 — Critique
Invoke the speckit-critique-run skill.
- Run the dual-lens (Product + Engineering) critique against
spec.mdandplan.mdbefore any tasks are generated. - For any 🎯 Must-Address findings, apply the suggested fixes to
spec.md/plan.mdautonomously and commit them — do not pause for user approval. - For 💡 Recommendations, apply them when the fix is clear and low-risk; otherwise note and move on.
- 🤔 Questions: resolve with your best judgment based on context (same rule as the Specify phase).
- If the verdict is 🛑 RETHINK, loop back to
speckit-plan(orspeckit-specifyif the spec itself is the problem), re-run the critique, then continue. - Commit the critique report and any spec/plan updates before moving on.
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.
- 10d ago First seen · 94 lines · 37 tokens per session scan A cf3dca91720d
speckit-auto-run is a skill published in the GitHub repository opsmill/infrahub-mcp (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 911 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
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.
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.
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.
meta-meeting-to-workflow
Use this meta-skill instead of answering directly when the user has meeting notes, transcripts, recordings, or rough discussion notes and wants them converted into decisions, owners, follow-ups, tasks, issues, or shareable minutes through multi-skill orchestration.