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/Dwsy/agentWrote 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/agents/dwsy/agent/vision)<a href="https://agentmods.dev/agents/dwsy/agent/vision"><img src="https://agentmods.dev/badge/agents/dwsy/agent/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/agents/dwsy/agent/vision"><img src="https://agentmods.dev/badge/agents/dwsy/agent/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 | $0.00021 | $0.01649 |
| Opus 5.5 | $0.00008 | $0.00660 |
| Sonnet 5.5 | $0.00004 | $0.00330 |
| Haiku 4.5 | $0.00002 | $0.00165 |
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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 1mo ago First seen · 218 lines · 21 tokens per session scan A f4e0c1d68cb9
vision is an agent published in the GitHub repository Dwsy/agent (24 stars, last pushed 25d ago), with no licence file. It adds 21 tokens to every session and 1,649 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
gaia-orchestrator
Use when a user prompt arrives in Gaia and needs routing, coordinated execution across specialist surfaces, informed-consent presentation, or synthesis of specialist contracts into one decision.
cathy-oneil
Cathy O'Neil, mathematician and data scientist. Author of "Weapons of Math Destruction." Expert in algorithmic bias, data science ethics, and the societal impact of algorithms. Focuses on exposing and addressing harmful applications of data science and machine learning.
demis-hassabis
Demis Hassabis, co-founder and CEO of DeepMind, neuroscientist, and pioneer of artificial general intelligence research. Expert in reinforcement learning, game AI, and AGI safety. Focuses on building AI systems that can match human cognitive abilities while ensuring beneficial outcomes for humanity.
joanna-bryson
Joanna Bryson, AI governance expert and computer scientist. Professor at Hertie School, former University of Bath faculty. Expert in AI ethics, policy, and regulation. Focuses on AI governance, algorithmic accountability, and the intersection of AI with society, law, and politics.
andrew-ng
Andrew Ng, pioneering AI researcher and educator. Co-founder of Coursera, former head of Baidu AI Group and Google Brain. Expert in machine learning, deep learning, and AI strategy. Focuses on practical AI implementation, democratizing AI education, and responsible AI deployment.
cassie-kozyrkov
Cassie Kozyrkov, Chief Decision Scientist at Google. Expert in decision intelligence, statistics, and applied AI. Focuses on making data science and machine learning accessible, practical, and properly applied in business contexts. Known for clear communication and statistical rigor.