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 JiuNian3219/architext --skill archi-design-patternsgit clone --depth 1 https://github.com/JiuNian3219/architextWrote 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/jiunian3219/architext/archi-design-patterns)<a href="https://agentmods.dev/skills/jiunian3219/architext/archi-design-patterns"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-design-patterns/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/jiunian3219/architext/archi-design-patterns"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-design-patterns.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.01595 |
| Opus 5 | $0.00013 | $0.00797 |
| Sonnet 5 | $0.00005 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
archi-design-patterns 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 10d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invocation
- Auto-invoke: No, not triggered by model based on description.
- Trigger location: Only explicitly called at corresponding step in
/archi.*protocols. - Execution context: Can execute inline in current context; when involving user questions must return to main dialogue.
- Boundary: Only assist generating options, interview questions or structured fragments, does not advance protocol steps independently.
Technical Design Structured Pattern Library
System Flow Positioning
/archi.plan step_4_generate → design.md § 2
↓
[This Skill] Pattern selection → Format generation → Self-check
↓
design.md § 2 Core Mechanisms content
Skill's Responsibility Boundary:
- Responsible for: Pattern selection guide, Standard format per pattern, Self-check list
- Not responsible for: design.md overall structure (see
design.template.md), Parameters/Invariants/Failure modes (see template §§ 3-5)
Pattern Selection Guide
Select ≥1 pattern based on mechanism characteristics. Same function can combine multiple (e.g. Connection management uses State Machine + Message processing uses Pipeline).
| Mechanism Characteristic | Recommended Pattern | Typical Scenario |
|---|---|---|
| Has discrete state set and inter-state transitions | State Machine | Connection management, Workflow engine, Component lifecycle, Auth flow |
| Data/request passes through ordered processing steps | Pipeline | Message decode chain, Middleware stack, Data transform pipeline, Request interceptor |
| Behavior depends on multiple condition combinations | Decision Matrix | Permission decision, Policy routing, Degradation rules, Feature flags |
| Two or more components have defined message exchange | Protocol | Client-server communication, Inter-process IPC, Event bus, Worker message |
Execution Flow: Select pattern → Fill corresponding standard format → Immediately execute self-check → Has unpassed items must fix then re-check → All pass before entering next mechanism.
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.
- 10d ago First seen · 152 lines · 26 tokens per session scan A 15b022cd36d3
archi-design-patterns is a skill published in the GitHub repository JiuNian3219/architext (14 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,595 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 skills, from other repositories
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
omh-frontend
This is a Hermes-native frontend workflow skill.
omh-accessibility-audit
This is a Hermes-native accessibility-audit workflow skill.
omh-visual-qa
This is a Hermes-native visual-qa workflow skill.
omh-design-orchestration
This is a Hermes-native design-orchestration workflow skill.