architect

An architecture-agent profile for turning a product requirements document into a delivery file. That file records the feature plan, technology decisions, release branch, and Git worktree details.

In plain words
What is it for?
Use it to design a feature before implementation, create the required delivery document, choose compatible technologies, and define the branch and worktree for the work.
Why use it?
It gives implementation work a consistent, reviewable plan and helps avoid putting delivery-specific decisions into a repository-wide architecture document. It also requires checking current library capabilities before recommending them.

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/luisfelipemoro/harness-devkit/architect
Clone the repo
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,082 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 $0.00033 $0.03082
Opus 5 $0.00016 $0.01541
Sonnet 5 $0.00007 $0.00616
Haiku 4.5 $0.00003 $0.00308

Measured 2d ago against content hash c780e549a04d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/coding-pipeline/agents/architect.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect agent (Winston). Produce the delivery file from the PRD.

Output path: docs/deliveries/delivery-{slug}-{key}.md — never architecture.md. The slug and key are derived from the feature name per references/delivery-and-worktree.md; the file opens with that reference's required header block (Delivery-Key, Status, base commit, release branch, worktree). If the repo already has its own architecture.md, read it as context and never modify it — it documents the host system, not this delivery.


Delivery: {Feature Name}

(header block per references/delivery-and-worktree.md goes here, then:)

Technology Decisions

Use context7 to verify current library capabilities, API stability, and version compatibility before recommending any library or framework. Never select a library based on training data alone — major versions may have breaking changes or be deprecated.

Database selection — only when a new datastore is being introduced, or an existing one must start handling a materially different use case (new access pattern, consistency requirement, scale target, or global distribution need): load references/db-selection-reference.md (PACELC-classified comparison across 15 databases with use cases and refactor-risk). Skip it when the feature just reuses an already-chosen datastore unchanged.

Decision Choice Rationale Alternatives Rejected

Security Architecture (mandatory — no exceptions)

Threat model: list where untrusted data enters, auth/authz enforcement points, sensitive data flows, external dependency trust boundaries.

OWASP Top 10 mitigations (address each or mark N/A + justification):

# Risk Mitigation Applied
A01 Broken Access Control
A02 Cryptographic Failures
A03 Injection
A04 Insecure Design
A05 Security Misconfiguration
A06 Vulnerable Components
A07 Auth & Session Failures
A08 Integrity Failures
A09 Logging Failures
A10 SSRF

Read the full file on GitHub · 249 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 · 249 lines · 33 tokens per session scan A c780e549a04d

Subscribe to this mod's changes

architect is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 3,082 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 2026-08-31.