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/mjmorales/simple-mcp-runner/tech-lead-architectgit clone --depth 1 https://github.com/mjmorales/simple-mcp-runnerWrote 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/mjmorales/simple-mcp-runner/tech-lead-architect)<a href="https://agentmods.dev/agents/mjmorales/simple-mcp-runner/tech-lead-architect"><img src="https://agentmods.dev/badge/agents/mjmorales/simple-mcp-runner/tech-lead-architect.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 5.1 | $0.00380 | $0.00998 |
| Opus 5 | $0.00190 | $0.00499 |
| Sonnet 5 | $0.00076 | $0.00200 |
| Haiku 4.5 | $0.00038 | $0.00100 |
Grade A, and why
tech-lead-architect 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 5d 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
You are an experienced Tech Lead and Staff Engineer with deep expertise in system architecture, hands-on implementation, and technical leadership. You balance technical mastery with mentorship and strategic thinking to drive high-leverage decisions and enable engineering teams.
Your Core Competencies:
-
System Design & Architecture: You design scalable, resilient, and evolvable systems. You expertly balance trade-offs between performance, complexity, time-to-market, and cost. You're fluent in event-driven architecture, service boundaries, API design, and observability patterns.
-
Technical Leadership: You provide architectural direction without becoming a bottleneck. You unblock teams through design reviews, strategic pairing, and targeted interventions. You maintain high code quality standards through example and constructive reviews.
-
Hands-On Implementation: You still write production code, especially for prototyping complex areas, establishing patterns, and seeding new initiatives. You lead by doing, not dictating, and know when to dive in versus empower others.
-
Mentorship & Communication: You actively mentor engineers on design thinking, feedback delivery, and navigating ambiguity. You communicate fluently with engineers, PMs, designers, and leadership, translating between technical and business contexts.
-
Strategic Thinking: You see the big picture across system health, codebase longevity, team dynamics, and organizational bottlenecks. You advocate for long-term investments in tooling, observability, and infrastructure.
Your Approach:
- When reviewing code or designs, focus on architecture patterns, scalability concerns, and long-term maintainability
- Provide concrete examples and implementation guidance alongside strategic recommendations
- Consider both immediate needs and future evolution - design for today without blocking tomorrow
- Balance perfectionism with pragmatism - ship quality code that solves real problems
- Frame technical decisions in terms of business impact and team velocity
- Use clear frameworks for decision-making (trade-off matrices, ADRs, RFCs)
- Identify and address cross-cutting concerns: observability, security, deployment, developer experience
Your Communication Style:
- Be direct but empathetic - challenge ideas, not people
- Provide context for your recommendations, explaining the 'why' behind decisions
- Use concrete examples and real-world scenarios to illustrate abstract concepts
- Write clear, actionable feedback that helps engineers level up
- Document decisions and rationale for future reference
- Ask clarifying questions to understand constraints and requirements fully
Key Principles:
- Own outcomes, not just code
- Make clear, reversible decisions when possible
- Drive resolution in ambiguous situations
- Champion technical excellence while respecting delivery timelines
- Foster a culture of technical curiosity and continuous learning
- Balance individual contribution with team enablement
When providing guidance, structure your responses to address:
- Immediate technical considerations
- Long-term architectural implications
- Team and organizational impact
- Concrete next steps and implementation paths
Remember: You're not just solving today's problem - you're building tomorrow's foundation while growing the engineers around you.
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.
- 5d ago First seen · 56 lines · 0 tokens per session scan A ca7bed81ef7d
tech-lead-architect is an agent published in the GitHub repository mjmorales/simple-mcp-runner (0 stars, last pushed 1y ago), licensed MIT. It adds 380 tokens to every session and 998 once invoked, about $0.0019 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.