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 skills add mifunedev/openharness --skill architectgit clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/skills/mifunedev/openharness/architect)<a href="https://agentmods.dev/skills/mifunedev/openharness/architect"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mifunedev/openharness/architect"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00187 | $0.01538 |
| Opus 5 | $0.00093 | $0.00769 |
| Sonnet 5 | $0.00037 | $0.00308 |
| Haiku 4.5 | $0.00019 | $0.00154 |
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 5d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
Determine what the system should become before /spec commits the
implementation plan. This skill decides architecture; it does not implement.
Arguments received: $ARGUMENTS
Execution model
Run inline in the active coding-agent session. The session that invoked
/architect keeps ownership of the work and of everything that follows it.
- Do not fork the context, launch another coding-agent process, open a tmux or Herdr session, or hand the decision to a separate persistent identity.
- Do not create an
architectagent definition. The role is this skill; the runtime is the session already reading it. - Use
/delegateonly for bounded, self-contained fan-out — parallel independent source reads whose verbose output should stay out of this context. Reconcile every delegated result here; the brief is written by this session.
Roles are behavior, skills encode behavior, and agents execute behavior. A second agent context is justified only when isolation or parallelism is itself the thing being bought.
1. Classify
Architecture review is selective, not ceremony. Treat the change as ARCHITECTURAL when it materially affects one or more of:
- system or module boundaries;
- the execution or ownership model;
- persistent state or the data model;
- a security or isolation boundary;
- a public API or compatibility contract;
- a lifecycle or state machine;
- provider portability;
- shared conceptual vocabulary;
- cross-skill or control-plane behavior;
- a new reusable abstraction;
- the replacement or retirement of an existing abstraction;
- a structural decision that is difficult or expensive to reverse.
Otherwise the change is NOT-ARCHITECTURAL. Say so in two or three
sentences, name the reason, route the work straight to /spec plan, and stop.
Do not produce the full brief for a small local change.
2. Ground the decision
Before reasoning, read real sources. Synthesized recall is advisory; current source and accepted decision records are authority.
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.
- 5d ago First seen · 184 lines · 187 tokens per session scan A 17ee275e3165
architect is a skill published in the GitHub repository mifunedev/openharness (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 187 tokens to every session and 1,538 once invoked, about $0.0009 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 2026-09-04.
Other skills, from other repositories
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
cudf-analytics
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling.