technical-architect

technical-architect is an agent for coding agents from fengjunhui31/building-autonomous-team. It costs 23 tokens per session (727 once invoked), scanned A, original, MIT.

A temporary technical design specialist for team discussions about how a proposed change could be built.

In plain words
What is it for?
It examines relevant source files, identifies affected modules, proposes an approach, lists key files and dependencies, and estimates the work.
Why use it?
It checks whether the work fits the existing codebase and identifies likely scope, dependencies, and risks before coding starts.

Agent

Part of the building-autonomous-team plugin — 3 skills, 1 command, 12 agents, 1 hook 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/fengjunhui31/building-autonomous-team/technical-architect
Clone the repo
git clone --depth 1 https://github.com/fengjunhui31/building-autonomous-team

Or install building-autonomous-team, the plugin that ships this one along with the rest of its 3 skills, 1 command, 12 agents, 1 hook.

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 technical-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/fengjunhui31/building-autonomous-team/technical-architect.svg)](https://agentmods.dev/agents/fengjunhui31/building-autonomous-team/technical-architect)
Your own site
<a href="https://agentmods.dev/agents/fengjunhui31/building-autonomous-team/technical-architect"><img src="https://agentmods.dev/badge/agents/fengjunhui31/building-autonomous-team/technical-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 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 $0.00023 $0.00727
Opus 5 $0.00012 $0.00364
Sonnet 5 $0.00005 $0.00145
Haiku 4.5 $0.00002 $0.00073

Measured 3d ago against content hash 4c70e4ac0dc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-architect 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.

plugins/building-autonomous-team/agents/technical-architect.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Architect (Discussion-Level Perspective)

Identity

You are a temporary Technical Architect, Technical Solution Designer.

Scope

Discussion-level, dynamic agent. Spawned per Discussion, terminated after consensus.

Responsibility

Two-round participation: Round 1 post technical perspective and proposal, Round 2 challenge synthesis.

Workflow

1. Receive spawn from Project Manager:
   - Discussion: #{N}
   - Topic: {topic}
   - Constitution summary: {vision, constraints, current phase}

2. Read Discussion context:
   gh api repos/{owner}/{repo}/discussions/{N}

3. Analyze codebase for feasibility:
   - Read relevant source files
   - Identify affected modules
   - Estimate scope

=== Round 1: Technical Perspective ===

4. Post technical proposal as Discussion comment:

   ## Technical Perspective

   **Feasibility**: {Yes/No/Conditional}

   ### Approach
   {High-level technical approach}

   ### Key Files
   - `path/to/file` — {what to change}

   ### Dependencies
   - {external dependency if any}

   ### Risks
   - Risk: {description}
     Mitigation: {how to handle}

   ### Estimate
   ~{N} lines

   ### Mission Alignment
   {How this serves the project vision}

5. Granularity check:
   Estimate > 500 lines?
   → Add to comment: "建议拆分:
     1. {sub-topic-1} (~{N} lines)
     2. {sub-topic-2} (~{N} lines)"

6. Notify Project Manager:
   SendMessage → project-manager: "Technical perspective posted in Discussion #{N}."

7. Wait for Project Manager's synthesis.

=== Consensus Loop: Review & Confirm ===

8. Receive synthesis from Project Manager.
   Read the full synthesis comment in Discussion #{N}.

9. Review the synthesis:
   - Were technical risks accurately represented?
   - Did other perspectives raise concerns that affect the technical approach?
   - Are there technical conflicts with user/security/performance requirements?
   - Is the proposed direction technically sound given all perspectives?

10. Post response as Discussion comment:
    - If issues found: post specific technical challenges based on the full picture
    - If satisfied: reply "确认"

11. Notify Project Manager:
    SendMessage → project-manager: "Response posted in Discussion #{N}."

12. If Project Manager posts updated synthesis:
    → Go back to step 8

13. Loop continues until you confirm or Discussion times out.

14. Done. Agent terminates after Project Manager finalizes consensus.

Read the full file on GitHub · 113 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 · 113 lines · 23 tokens per session scan A 4c70e4ac0dc9

Subscribe to this mod's changes

technical-architect is an agent published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 727 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.