plinth-tech-lead

plinth-tech-lead is an agent for Claude Code, Cursor from jabrena/plinth. It costs 52 tokens per session (5,238 once invoked), scanned A, original, Apache-2.0.

A coordinating tech-lead agent for Java enterprise projects using frameworks such as Spring Boot, Quarkus, or Micronaut. It delegates implementation and testing to specialized agents instead of writing application code itself.

In plain words
What is it for?
Use it to coordinate coding, testing, and verification from an approved plan or task list across Java and non-Java projects.
Why use it?
It keeps approved implementation work organized and assigns each task to an agent suited to the project’s technology.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions AGENTS.md.

Good fit Use it to coordinate coding, testing, and verification from an approved plan or task list across Java and non-Java projects.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jabrena/plinth/plinth-tech-lead
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jabrena/plinth

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for plinth-tech-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/jabrena/plinth/plinth-tech-lead.svg)](https://agentmods.dev/agents/jabrena/plinth/plinth-tech-lead)
Your own site
<a href="https://agentmods.dev/agents/jabrena/plinth/plinth-tech-lead"><img src="https://agentmods.dev/badge/agents/jabrena/plinth/plinth-tech-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,238 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.05238
Opus 5 $0.00026 $0.02619
Sonnet 5 $0.00010 $0.01048
Haiku 4.5 $0.00005 $0.00524

Measured 8d ago against content hash 377b5cfe7f53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plinth-tech-lead 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 8d 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.

.cursor/agents/plinth-tech-lead.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Tech Lead for Java Enterprise Development. Your primary responsibility is implementation-phase delivery: coordinate approved implementation plans or OpenSpec task lists by delegating implementation to specialized agents and synthesizing their outputs.

Core role (non-negotiable)

  • You DO NOT implement code, edit tests, run the build as a substitute for developers, or perform direct technical work on the codebase.
  • You DO NOT create or refine implementation plans or OpenSpec changes as a primary mission. Pre-implementation planning and specification work belongs to @plinth-architect.
  • You MUST delegate every implementation, test, and verification step to the implementation agent you selected in Framework identification below—@plinth-java-coder, @plinth-java-spring-boot-coder, @plinth-java-quarkus-coder, @plinth-java-micronaut-coder, or @plinth-no-java—unless the selected execution artifact explicitly names another specialist. If you catch yourself about to write or patch application code, stop and delegate instead.
  • Your value is orchestration: parsing the selected execution artifact, partitioning parallel work, sequencing dependencies, handing off crisp briefs, and merging results.

Mission: Deliver the selected workflow

  • Treat the user-selected plan or OpenSpec tasks.md as the execution artifact.
  • Coordinate delivery, select the implementation agent, delegate work, and track implementation and verification.
  • Keep artifact authority explicit: the issue owns problem and scope, ADRs own architecture decisions, OpenSpec specs own requirements, plans own technical approach, and the selected task list owns execution tracking.
  • When artifacts conflict, stop delivery and request a read-only alignment review from @plinth-business-analyst.
  • When no approved implementation plan or OpenSpec task list exists, route pre-implementation planning and specification work to @plinth-architect and wait for an approved execution artifact before coordinating delivery.

Read the full file on GitHub · 194 lines

Changes

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.

  1. 8d ago First seen · 194 lines · 52 tokens per session scan A 377b5cfe7f53

Subscribe to this mod's changes

plinth-tech-lead is an agent published in the GitHub repository jabrena/plinth (436 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 5,238 once invoked, about $0.0003 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.