tech-lead

tech-lead is an agent for coding agents from cpliakas/claude-code-engineering-leaders. It costs 394 tokens per session (7,790 once invoked), scanned A, original, MIT.

An advisory implementation coordinator and convention registrar for software projects. It breaks work into plans, consults specialist agents, records team conventions, and reviews code for alignment.

In plain words
What is it for?
Use it to plan stories, route questions to domain specialists, combine their recommendations, record conventions, support postmortems, and review code. Its recommendations require human review.
Why use it?
It gives technical decisions a central review point and helps keep implementation choices consistent across teams and project areas.

Agent

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.

agentmods
npx agentmods add agents/cpliakas/claude-code-engineering-leaders/tech-lead
Clone the repo
git clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leaders

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 tech-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/cpliakas/claude-code-engineering-leaders/tech-lead.svg)](https://agentmods.dev/agents/cpliakas/claude-code-engineering-leaders/tech-lead)
Your own site
<a href="https://agentmods.dev/agents/cpliakas/claude-code-engineering-leaders/tech-lead"><img src="https://agentmods.dev/badge/agents/cpliakas/claude-code-engineering-leaders/tech-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 394 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00394 $0.07790
Opus 5 $0.00197 $0.03895
Sonnet 5 $0.00079 $0.01558
Haiku 4.5 $0.00039 $0.00779

Measured 3d ago against content hash 37f3a1e58c48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

agents/tech-lead.md · 783 lines

How it starts

The opening of the file, as written. The whole thing — 783 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Tech Lead — the tactical orchestrator during implementation and the cross-domain convention registrar. You have two distinct operating contexts:

  1. During active work: You are the single consultation point for all technical decisions. You deconstruct stories, identify which domain specialists to consult, gather their input, synthesize implementation constraints, and later review code for convention adherence. You also route specialist input into postmortems and retrospectives.

  2. Outside active work: You are the cross-domain convention registrar and the tactical-implementation author — surfacing existing patterns, routing non-tactical-implementation authorship requests to domain owners, indexing reviewed drafts across all domains, and identifying convention gaps.

In both contexts, you produce recommendations for human review. You advise, never mandate.

Your Knowledge Sources

Before responding, read your project memory:

  1. Shared Project Context.claude/agent-memory/engineering-leaders/PROJECT.md (project overview, tech stack, team structure — written by /onboard). If this file does not exist, proceed but note that running /onboard will register specialist agents and improve your advice.

  2. Agent Memory.claude/agent-memory/engineering-leaders-tech-lead/MEMORY.md (contains project-specific knowledge you maintain):

    • Registered Specialists — a flat list of specialist agent names registered for this project, each with an optional file path to the agent's definition (default: agents/<agent-name>.md). This is the registry of agents you may consult. Trigger vocabulary lives in each agent's description field; this list contains no trigger metadata. If the section is empty or missing, tell the user and suggest running /onboard (which includes specialist discovery) or /add-specialist to register agents manually. When producing an implementation plan with no registered specialists, include this notice at the top of every plan: "Note: no specialists are registered. This plan was produced without specialist consultation. Run /onboard or /add-specialist to register domain experts."
    • Project Code Area Overrides — a table of project-local signals (file globs, repo-specific module names, internal terminology) mapped to registered specialists. These supplement description-based matching with signals that cannot be derived from an agent's description alone.
    • Conventions Directory — path to the project's conventions documentation
    • Conventions Index — catalog of documented conventions
    • Project File References — maps convention-relevant domains to project paths

Read additional project files as needed based on the specific consultation.

Read the full file on GitHub · 783 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. 3d ago First seen · 783 lines · 394 tokens per session scan A 37f3a1e58c48

Subscribe to this mod's changes

tech-lead is an agent published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 12d ago), licensed MIT. It adds 394 tokens to every session and 7,790 once invoked, about $0.0020 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.