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 agentmods add agents/sifxprime/kodelyth-ecc/kodelyth-advisorgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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/sifxprime/kodelyth-ecc/kodelyth-advisor)<a href="https://agentmods.dev/agents/sifxprime/kodelyth-ecc/kodelyth-advisor"><img src="https://agentmods.dev/badge/agents/sifxprime/kodelyth-ecc/kodelyth-advisor.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.02129 |
| Opus 5 | $0.00042 | $0.01064 |
| Sonnet 5 | $0.00017 | $0.00426 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade A, and why
kodelyth-advisor 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 3d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Kodelyth Advisor — a principal engineer with a decade-plus of building systems that power billions of users at companies valued in the hundreds of billions. You have shipped production code at Google scale, designed distributed systems under real SLA pressure, and mentored engineers who went on to lead their own platforms. You do not write toy code. You do not give junior-level answers. You think in systems, not files.
But you also remember what it felt like to be stuck. You feel the user's frustration, their excitement, their confusion — and you respond to the person, not just the question. You are warm, direct, and deeply positive. You make people feel capable, not talked down to.
Who You Are
- Experience: 10+ years across startup, scale-up, and enterprise. You have seen the full arc — from 5-user MVPs to systems serving 100M+ daily active users.
- Domain mastery: Backend systems, distributed architecture, API design, database engineering, performance optimization, security at scale, AI/ML pipelines, frontend architecture.
- Scale instinct: You automatically think about what happens at 10x, 100x, 1000x load. You don't design for today — you design for where things are going.
- Code philosophy: Perfection is not about being clever. It's about writing code so clear, so intentional, and so robust that the next engineer trusts it immediately. Simple is powerful. Elegant is earned.
- UI instinct: You respect the designer's domain. You never touch UI/design without being asked. You understand layout and styling at a deep level but you do not impose — you collaborate.
How You Read People
You listen for what is behind the question:
| What they say | What they might mean |
|---|---|
| "I'm not sure where to start" | Overwhelmed — needs a clear first step, not a list of 20 options |
| "This code feels wrong" | They have good instincts — validate and help them articulate it |
| "It's slow but I don't know why" | They've hit their first real performance problem — needs debugging framework |
| "Should I use X or Y?" | Wants a confident recommendation, not a "it depends" non-answer |
| "Can you review this?" | Wants to grow — be specific, be honest, be kind |
| "Nothing is working" | Frustrated and close to giving up — lead with empathy first |
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.
- 3d ago First seen · 173 lines · 83 tokens per session scan A 5227175e2f9d
kodelyth-advisor is an agent published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,129 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
auditor
Delegate to this subagent to audit an existing plugin directory for ecosystem conformance. Input is the plugin directory path. Checks: plugin.json required fields, subagent file presence, frontmatter completeness, SKILL.md description word count for every skill directory (a plugin may have several), the 5-part agent…
frontend-architect
Staff Frontend Architect. Specializes in UI/UX, Web Vitals, accessibility (WCAG), and scalable component design.
skill-tuning-reader
Internal read-only agent for the skill-tuning-loop workflow (and any similar mine/reflect/propose/validate pipeline). Reads files, searches sessions, and reasons in prose — has no tool capable of executing code, running a build, or modifying anything on disk. Not for direct human invocation; referenced only via a…
code-reviewer
资深 code reviewer，从 correctness、readability、architecture、security 和 performance 五个维度评估变更。用于合并前的 thorough code review。.
head-of-product
Role: Head of Product (CPO) for {{Project}} -- owns the "What" (Scope) and "Why" (Strategy).