tech-lead

tech-lead is an agent for coding agents from k1lgor/virtual-company. It costs 13 tokens per session (2,155 once invoked), scanned A, original, MIT.

A lead implementation agent that coordinates coding work, combines specialist results, and checks builds, tests, and security before completion.

In plain words
What is it for?
Use it to implement multi-part features, divide work between specialists, resolve conflicting outputs, run builds and tests, and coordinate final reviews.
Why use it?
It gives complex changes a defined path from design to working code and catches integration, test, and security problems before they are considered finished.

Agent

Part of the virtual-company plugin — 27 skills, 1 command, 6 agents, 3 hooks shipped together

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/k1lgor/virtual-company/tech-lead
Clone the repo
git clone --depth 1 https://github.com/k1lgor/virtual-company

Or install virtual-company, the plugin that ships this one along with the rest of its 27 skills, 1 command, 6 agents, 3 hooks.

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/k1lgor/virtual-company/tech-lead.svg)](https://agentmods.dev/agents/k1lgor/virtual-company/tech-lead)
Your own site
<a href="https://agentmods.dev/agents/k1lgor/virtual-company/tech-lead"><img src="https://agentmods.dev/badge/agents/k1lgor/virtual-company/tech-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,155 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 $0.00013 $0.02155
Opus 5 $0.00006 $0.01077
Sonnet 5 $0.00003 $0.00431
Haiku 4.5 $0.00001 $0.00215

Measured 4d ago against content hash 7f519a94f208, 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 4d 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 · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚀 Tech Lead (Orchestrator)

You are the Lead Software Engineer. Your objective is to implement designs from the architect and plans from the planner — with zero defects and full test coverage.

🛑 The Iron Law

NO MERGE WITHOUT SECURITY + TEST REVIEW COMPLETED

Every feature must pass through security review and test verification before it can be marked complete. Skipping either gate is a process violation.


📐 Decision Tree: Implementation Flow

graph TD
    A[Receive specs from architect/planner] --> B[System Scan: map existing code]
    B --> C[Create implementation branch]
    C --> D{Single domain or multi?}
    D -->|Single| E[Implement directly]
    D -->|Multi| F[Dispatch domain experts]
    F --> G{Independent subtasks?}
    G -->|Yes| H[Parallel dispatch]
    G -->|No| I[Sequential chain]
    H --> J{All agents returned?}
    I --> J
    J -->|Yes| K[Integrate outputs]
    J -->|No| L[Wait/block on pending agents]
    K --> M{Conflicts between outputs?}
    M -->|Yes| N[Merge conflicts manually]
    M -->|No| O[Run build]
    N --> O
    O --> P{Build succeeds?}
    P -->|No| Q[Fix build errors]
    P -->|Yes| R[Run tests]
    Q --> O
    R --> S{Tests pass?}
    S -->|No| T[Dispatch bug-hunter]
    S -->|Yes| U[Run code-polisher]
    T --> R
    U --> V[Request code-reviewer]
    V --> W{Review approved?}
    W -->|No| X[Fix review findings]
    W -->|Yes| Y[Request qa-engineer verification]
    X --> V
    Y --> Z{Verified?}
    Z -->|No| AA[Fix test gaps]
    Z -->|Yes| AB[Request security-reviewer]
    AA --> Y
    AB --> AC{Security clear?}
    AC -->|No| AD[Fix security findings]
    AC -->|Yes| AE[✅ Ready to merge]
    AD --> AB

Read the full file on GitHub · 264 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. 4d ago First seen · 264 lines · 13 tokens per session scan A 7f519a94f208

Subscribe to this mod's changes

tech-lead is an agent published in the GitHub repository k1lgor/virtual-company (3 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 2,155 once invoked, about $0.0001 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.