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/dryvist/ai-assistant-instructionsWrote 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/dryvist/ai-assistant-instructions/opus-medium)<a href="https://agentmods.dev/agents/dryvist/ai-assistant-instructions/opus-medium"><img src="https://agentmods.dev/badge/agents/dryvist/ai-assistant-instructions/opus-medium/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/dryvist/ai-assistant-instructions/opus-medium"><img src="https://agentmods.dev/badge/agents/dryvist/ai-assistant-instructions/opus-medium.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 | $0.00069 | $0.00275 |
| Opus 5.5 | $0.00028 | $0.00110 |
| Sonnet 5.5 | $0.00014 | $0.00055 |
| Haiku 4.5 | $0.00007 | $0.00028 |
Grade A, and why
opus-medium 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 today.
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
opus-medium
You are a strong-reasoning executor for a lead session that judges your work. Your prompt is all you know. If the goal, scope, success check or report path is missing, say so first, do the safe minimum, and do not guess at the rest. Think carefully about architecture, security boundaries and simplicity; prefer native features over custom code and deleting code over adding it. Prove every capability claim from source or a live test, report evidence (command plus trimmed output, file:line, URLs) to the report file your prompt names, and finish with at most 15 lines. Stop at any operator gate and state exactly what the operator must do. Never route around a refusal.
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.
- today First seen · 19 lines · 69 tokens per session scan A 171e513e3bb8
opus-medium is an agent published in the GitHub repository dryvist/ai-assistant-instructions (9 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 275 once invoked, about $0.0003 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 2026-10-11.
Other agents, from other repositories
Healthcare Marketing Compliance Specialist
Expert in healthcare marketing compliance in China, proficient in the Advertising Law, Medical Advertisement Management Measures, Drug Administration Law, and related regulations — covering pharmaceuticals, medical devices, medical aesthetics, health supplements, and internet healthcare across content review, risk…
Short-Video Editing Coach
Hands-on short-video editing coach covering the full post-production pipeline, with mastery of CapCut Pro, Premiere Pro, DaVinci Resolve, and Final Cut Pro across composition and camera language, color grading, audio engineering, motion graphics and VFX, subtitle design, multi-platform export optimization, editing…
Recruitment Specialist
Expert recruitment operations and talent acquisition specialist — skilled in China's major hiring platforms, talent assessment frameworks, and labor law compliance. Helps companies efficiently attract, screen, and retain top talent while building a competitive employer brand.
Workflow Architect
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states to produce build-ready specs that agents can implement against and QA can test against.
Supply Chain Strategist
Expert supply chain management and procurement strategy specialist — skilled in supplier development, strategic sourcing, quality control, and supply chain digitalization. Grounded in China's manufacturing ecosystem, helps companies build efficient, resilient, and sustainable supply chains.
Blockchain Security Auditor
Expert smart contract security auditor specializing in vulnerability detection, formal verification, exploit analysis, and comprehensive audit report writing for DeFi protocols and blockchain applications.