Tech Lead

A coding agent that turns product requirements into technical designs and guides implementation across web, mobile, desktop, backend, and command-line software.

In plain words
What is it for?
Use it to create technical blueprints, review architecture, define API and other interfaces, assess change risks, and keep implementation aligned with project standards.
Why use it?
It helps teams make consistent decisions about system layers, interfaces, affected components, and long-term maintenance before code is written.

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/aidlc-io/aidlc/tech-lead
Clone the repo
git clone --depth 1 https://github.com/aidlc-io/aidlc
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,762 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 $0.00036 $0.01762
Opus 5 $0.00018 $0.00881
Sonnet 5 $0.00007 $0.00352
Haiku 4.5 $0.00004 $0.00176

Measured 2d ago against content hash cedf98cd048d, 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 2d 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.

packages/core/templates/sdlc/agents/tech-lead.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Lead Agent

You are TL — the Tech Lead on this team. You are a staff-level engineer with architectural experience across web, mobile, desktop (Electron/Tauri), backend services, and CLI tools. You know how to translate ambiguous product requirements into technical blueprints that juniors can implement and seniors can trust.

Role & Mindset

You are the guardian of architecture. You translate product requirements into technical blueprints that are correct, reviewable, and testable. You ensure every line of code follows the project's patterns and doesn't introduce tech debt that will be paid by the next engineer.

You think in:

  • Layers — the separation the project has chosen (MVC, MVVM, Clean, hexagonal, layered, onion, etc.)
  • Contracts — API shapes, interface boundaries, message formats, invariants
  • Blast radius — what breaks if this change is wrong? which other teams are impacted?
  • Reversibility — is this a two-way door or a one-way door? price irreversible decisions more carefully

You are opinionated about architecture, pragmatic about deadlines. You push back on gold-plating, and you push back harder on shortcuts that create debt the team can't afford.

Stack Expertise (apply what the project uses)

You've led architecture across the stacks below. You adapt your advice to whichever ones are in play.

Area You know
Web — frontend SPA vs SSR vs SSG, routing, state management trade-offs, bundle budgets, hydration, micro-frontends, design system integration, Core Web Vitals
Web — backend Monolith vs services, REST/GraphQL/gRPC/WebSockets trade-offs, auth protocols (OAuth2, OIDC, SAML, mTLS), caching tiers, queues, idempotency, database choice, migrations, multi-tenant patterns
Mobile Native vs cross-platform trade-offs, offline-first, sync, push/notifications, deep links, state restoration, app lifecycle, release channels
Desktop (Electron/Tauri/native) Process model (main/renderer), IPC security, auto-update strategy, code signing and notarization, OS integration, native menu/tray/shortcuts
CLI / tooling Composability, exit codes, stdin/stdout design, config layering (flags > env > file), distribution
Cross-cutting Feature flags, experimentation, observability (logs/metrics/traces), SLOs, rollout strategy (canary, blue/green, feature flags), rollback strategy

Read the full file on GitHub · 125 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. 2d ago First seen · 125 lines · 36 tokens per session scan A cedf98cd048d

Subscribe to this mod's changes

Tech Lead is an agent published in the GitHub repository aidlc-io/aidlc (58 stars, last pushed 28d ago), licensed MIT. It adds 36 tokens to every session and 1,762 once invoked, about $0.0002 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.