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.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/vision)<a href="https://agentmods.dev/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/vision"><img src="https://agentmods.dev/badge/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/vision/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/vision"><img src="https://agentmods.dev/badge/commands/michelkerkmeester/skilled-agent-harness_spec-driven-loops/vision.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 | $0.00009 | $0.00415 |
| Opus 5 | $0.00005 | $0.00208 |
| Sonnet 5 | $0.00002 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
vision 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 8d 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.
What it actually says
/vision
1. PURPOSE
Use Cursor's sk-vision MCP tool to read the user's most recent image locally, then answer from the returned evidence.
2. OVERVIEW
Cursor reaches sk-vision through its MCP tools. The sk_vision_inspect tool accepts the attached image or its path and returns a <SK-VISION> block containing scene analysis, a caption, and exact OCR, or an answer to a supplied question.
3. CONTRACT
Input: $ARGUMENTS — an optional question about the most recent image.
Output: A concise answer synthesized from the sk_vision_inspect result. Treat OCR as exact evidence; treat scene and caption as interpretation.
4. INSTRUCTIONS
- Call the
sk_vision_inspectMCP tool on the user's most recent image, using the attached image or its path. - When
$ARGUMENTSis non-empty, pass it as the tool'squestionparameter. - When
$ARGUMENTSis empty, omitquestionand request the full read: scene, caption, and OCR. - Answer using the tool's
<SK-VISION>output. Synthesize the evidence instead of dumping the raw block. - Treat OCR as exact and verbatim. Treat scene and caption as interpretation and hedge uncertain claims.
- Never invent details beyond the tool evidence.
5. HARD RULES
- If there is no recent image, ask the user to attach one and run
/visionagain. - If the tool errors, report the error briefly and do not fabricate an analysis.
- If multiple images are present, use only the most recent one.
User request: $ARGUMENTS
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.
- 8d ago First seen · 47 lines · 9 tokens per session scan A daef8cbb17bd
vision is a command published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 415 once invoked, about $0.0000 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 commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.