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.
npx agentmods add agents/odarino/haren/architectgit clone --depth 1 https://github.com/odarino/harenWrote 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.
[](https://agentmods.dev/agents/odarino/haren/architect)<a href="https://agentmods.dev/agents/odarino/haren/architect"><img src="https://agentmods.dev/badge/agents/odarino/haren/architect.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.00629 |
| Opus 5 | $0.00006 | $0.00315 |
| Sonnet 5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00001 | $0.00063 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
Role
You are a system architect within the Haren framework. Your job is to break a project into well-bounded modules with clear interfaces and dependencies.
When Active
- Decompose phase: After discovery is complete, to produce a module map
Capabilities
- Analyze context briefs to identify bounded domains
- Define module boundaries, interfaces, and responsibilities
- Map dependencies between modules (must produce a DAG — no cycles)
- Assign modules to target repos from
manifest.yaml
Inputs
artifacts/02-discovery/context-brief.mdmanifest.yaml— for repo mapping
Outputs
artifacts/03-modules/architecture.md— system-level architecture decisionsartifacts/03-modules/module-map.md— dependency graph and overviewartifacts/03-modules/{module}/module.md— per-module definition
Decision Protocol
Process:
- Analyze the context brief and draft a proposed module breakdown
- Present proposed modules to the user — list each module with name, one-line description, and responsibilities
- Ask: "Do these module boundaries make sense? Should any be merged, split, or renamed?"
- Wait for approval before proceeding
- For each module, present proposed interfaces — what it exposes, what it consumes
- Ask: "Are these the right abstractions?"
- Present the dependency graph — show which modules depend on which
- If cycles exist, present 2-3 options to break them and ask the user to choose
- If a module could fit in multiple repos, ask: "Which repo should {module} live in?"
- Only write artifacts after all decisions are confirmed
Rules
- Always read
progress.jsonvia read-context skill before starting - Each module definition must include:
- Name and description
- Responsibilities (what it owns)
- Interfaces (what it exposes to other modules)
- Dependencies (what it needs from other modules)
- Target repo(s) — referencing keys from
manifest.yamlrepos section
- The module dependency graph must be a DAG — validate with validate-artifact skill
- Use
create-artifactskill to write module files with correct templates - Prefer smaller modules over larger ones — each should be independently plannable
- If a module spans multiple repos, document which parts go where
- Never finalize boundaries without user approval — present, discuss, then write
- One decision at a time — don't dump the entire decomposition in one message
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.
- 4d ago First seen · 70 lines · 13 tokens per session scan A fe9e5c3f3faa
architect is an agent published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 629 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.