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 kostyk348/sint-ua-v2.1 --skill ownergit clone --depth 1 https://github.com/kostyk348/sint-ua-v2.1Wrote 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/kostyk348/sint-ua-v2.1/owner)<a href="https://agentmods.dev/skills/kostyk348/sint-ua-v2.1/owner"><img src="https://agentmods.dev/badge/skills/kostyk348/sint-ua-v2.1/owner/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/kostyk348/sint-ua-v2.1/owner"><img src="https://agentmods.dev/badge/skills/kostyk348/sint-ua-v2.1/owner.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 | $0.00047 | $0.00999 |
| Opus 5 | $0.00023 | $0.00500 |
| Sonnet 5 | $0.00009 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
owner 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model of the project owner. Helps agent make decisions aligned with owner's style. Written by owner, updated by owner. Agent reads but does not modify. Honest > flattering. If something here is wrong, update it.
WHO
Konstantin — electrical engineer, Saint Petersburg State Electrotechnical University (ЛЭТИ). Systems-level focus. Works across OS design, memory allocation, control systems, agent protocols, reverse engineering. Uses AI extensively to formalize and document ideas.
DECISION STYLE
- Correctness over cleverness. A working simple solution beats an elegant broken one.
- Measure before optimizing. Won't accept "probably faster" — needs numbers.
- Ensemble thinking. Prefers solutions robust across conditions over optimal on nominal case.
- Worst-case aware. In real-time/systems work: worst-case matters more than mean.
- Pragmatic about complexity. Will add complexity if it earns its place with benchmarks. Won't add it speculatively.
- Honest assessment preferred. Wants to know when something won't work, not reassurance.
KNOWN PREFERENCES
- Language: Rust for systems/performance, Python for tooling/experiments, C for embedded/Vita
- Platform: Artix Linux + Hyprland primary, Windows 10 secondary
- Tooling: lightweight, efficient. Avoids heavy frameworks when stdlib works.
- Documentation: writes with AI assistance — concepts are his, AI helps formalize. Views this as unproblematic.
- Working style: collaborative "we" framing with AI. Iterative, idea-first.
- Output format: prefers concrete over abstract. Numbers, code, examples over explanations.
ANTI-PREFERENCES
Things to avoid proposing. These will be declined.
- Heavy dependencies for simple tasks. Don't suggest pytorch for something numpy handles.
- Speculative complexity. Don't add abstraction layers "for future flexibility" without a concrete case.
- Entropy-aware wave selection in MPTC. Already tried. Doesn't work. Don't suggest again.
- Lifecycle float arithmetic in allocator. Same — tried, overhead > benefit.
- Self-verifying agents. Core SINT principle: never suggest single-agent verification loops.
- Verbose reassurance. Don't say "great question!" or pad responses. Get to the point.
- Premature publication pressure. Ideas develop at their own pace. Don't push to "ship" prematurely.
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 · 81 lines · 47 tokens per session scan A e7f4a1da4002
owner is a skill published in the GitHub repository kostyk348/sint-ua-v2.1 (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 999 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
engrama-onboard
Build a personalized Engrama memory graph for any user through a conversational interview. Use this skill whenever someone says "set up Engrama", "create my graph", "onboard", "build my profile", "configure Engrama for me", or asks how to start using Engrama. Also use when the user mentions they have a different role…
handoff
Save a session handoff to Engram for future sessions. Captures decisions, todos, blockers, mental model, and next steps as a structured memory. Use when the user wants to preserve session context before ending work.
read-handoffs
Resume a session by loading recent handoffs from Engram. Use at the start of a session or when the user wants to review what was done previously.
memx
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
memory-review
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
context-loader
Session-start context loading -- loads historical decisions, issues, and patterns from Pensyve to provide cross-session continuity. Use at session start or when switching context.