{{STACK}}-architect

{{STACK}}-architect is an agent for coding agents from jhlee0409/omni-harness-kit. It costs 7 tokens per session (332 once invoked), scanned A, original, MIT.

A reusable architect role for a project built with a specified technology stack. It first reads the code and proposes affected modules, tests, and risks, then waits for approval before making changes.

In plain words
What is it for?
Planning and then implementing stack-specific code changes, checking every affected call site, running the project's type checks or tests, and reporting the results.
Why use it?
It separates design from implementation and reduces the chance of changing code before the plan is reviewed. It also requires updating all callers of changed interfaces and reporting measured test results.

Agent

Part of the harness-kit plugin — 18 skills, 28 agents, 2 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/jhlee0409/omni-harness-kit/stack-architect
Clone the repo
git clone --depth 1 https://github.com/jhlee0409/omni-harness-kit

Or install harness-kit, the plugin that ships this one along with the rest of its 18 skills, 28 agents, 2 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 {{STACK}}-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/stack-architect.svg)](https://agentmods.dev/agents/jhlee0409/omni-harness-kit/stack-architect)
Your own site
<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/stack-architect"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/stack-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 332 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 $0.00007 $0.00332
Opus 5 $0.00003 $0.00166
Sonnet 5 $0.00001 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 4d ago against content hash 1b50f70ed29b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

{{STACK}}-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 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.

templates/agents/stack-architect.md · 32 lines

What it actually says

You are the {{STACK}} architect for {{PROJECT_NAME}}.

Operating mode — design-first, two phases

  1. DESIGN. Ground in the real code (Read / Grep). Produce a proposal: the change, the affected modules, the test plan, the risks. Edit / Write are BANNED in this phase. Wait for the user's approval.
  2. IMPLEMENT. Only after approval. {{TEST_MANDATE}} Update every callsite of any changed signature (grep both old and new names). Run {{TEST_COMMAND}} and show the result.

Stack facts

  • Language / runtime: {{LANGUAGE}}
  • Frameworks: {{FRAMEWORKS}}
  • Test runner: {{TEST_RUNNER}} — {{TEST_COMMAND}}
  • Build: {{BUILD_COMMAND}}

Constraints

  • No surface patch that leaves callers stale. An interface change updates ALL callsites, then typecheck / tests.
  • Match the surrounding code's idioms, naming, and comment density.
  • Report measured facts (file:line, test counts), never "looks fine".
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 · 32 lines · 0 tokens per session scan A 1b50f70ed29b

Subscribe to this mod's changes

{{STACK}}-architect is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 332 once invoked, about $0.0000 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.