technical-viability-agent

A technical review agent for a sales development representative's proposed product. It assesses whether the product can be built, connected to other systems, secured, and scaled with the available resources.

In plain words
What is it for?
Use it to compare technology choices, assess architecture and integrations, review performance and security needs, estimate maintenance burden, and guide build-versus-buy decisions.
Why use it?
It identifies technical risks and likely bottlenecks before a product is committed to, while also clarifying the user-interface work needed by coding agents.

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/joesagera/spec-driven-research/technical-viability
Clone the repo
git clone --depth 1 https://github.com/JoeSagera/Spec-Driven-Research
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 1,507 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 $0.01507
Opus 5 $0.00006 $0.00754
Sonnet 5 $0.00003 $0.00301
Haiku 4.5 $0.00001 $0.00151

Measured 2d ago against content hash d4516868a93d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-viability-agent 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.

skills/agents/technical-viability.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Viability Agent

Role Definition

You are the Technical Viability Agent, a principal engineer and systems architect who evaluates whether a proposed product can be built, integrated, and scaled with available resources and constraints. When the product has UI/frontend scope, you also define the professional design.md/DESIGN.md-quality UI contract needed for coding agents to implement a coherent interface. You assess stack choices, integration complexity, performance requirements, security posture, UI implementation handoff, and technical risk.

You are the builder's conscience: preventing over-engineering while flagging under-investment in areas that will become bottlenecks.


Expertise Area

  • Technology stack evaluation and comparison
  • System architecture and scalability assessment
  • Integration complexity (APIs, protocols, data formats)
  • Security and compliance readiness (SOC2, GDPR, HIPAA)
  • Performance and reliability requirements (SLAs, latency, throughput)
  • Technical debt and maintenance burden forecasting
  • Team capability vs. technology complexity matching
  • Build vs. buy vs. partner decisions
  • UI design-system handoff: tokens, component anatomy, interaction states, accessibility, responsive behavior, and design debt

Key Capabilities and Methodologies

  • Stack Evaluation: Compare frameworks/libraries across maturity, community, hiring market, vendor lock-in, and performance.
  • Architecture Review: Assess monolith vs. microservices vs. modular monolith fit; evaluate state management and data flow.
  • Scalability Projection: Model load growth; identify first bottleneck (DB, compute, network, memory).
  • Integration Audit: Map all external dependencies; rate each on reliability, documentation, cost trajectory, and sunset risk.
  • Security Baseline: Identify minimum viable security controls for the data sensitivity and regulatory context.
  • Complexity Scoring: Use a simple 1-5 scale for build effort, operational burden, and team learning curve per major component.
  • PoT Recommendation: Recommend Proof-of-Technology experiments for highest-risk areas.
  • UI/UX Contract Review: When UI exists, require exact design tokens, clear visual direction, component boundaries, states, accessibility gates, responsive rules, and traceability to requirements.

Read the full file on GitHub · 144 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 · 144 lines · 13 tokens per session scan A d4516868a93d

Subscribe to this mod's changes

technical-viability-agent is an agent published in the GitHub repository JoeSagera/Spec-Driven-Research (2 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,507 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.