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-intent-normalizergit 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-intent-normalizer)<a href="https://agentmods.dev/skills/jiunian3219/architext/archi-intent-normalizer"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-intent-normalizer/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-intent-normalizer"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-intent-normalizer.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 | $0.00043 | $0.01634 |
| Opus 5 | $0.00022 | $0.00817 |
| Sonnet 5 | $0.00009 | $0.00327 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
archi-intent-normalizer 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 9d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invocation
- Auto-invoke: Yes, called by
00_system.mdFront Pipeline. - Trigger location: Before user request enters protocol routing.
- Execution context: When subagent supported must execute in independent subagent/independent context; only fallback to
NO-SUBAGENT/NO-SKILLinline execution when no subagent. - Boundary: Only produce structured intermediate artifacts, does not execute protocols, does not modify project files.
Architext Intent Normalizer
Purpose
Convert user's original words into structured Intent Card. This Skill only does semantic understanding and routing suggestions, does not read large files, does not modify files, does not execute commands.
Inputs
user_message: User's current message full text.recent_context: Brief context from recent conversation still affecting intent judgment.explicit_command: If user input starts with/archi., record original command; otherwisenull.known_state: Lightweight state caller can provide, e.g. roadmap id list, current discussion file, current task id.
Output Contract
Only output one JSON code block, no explanatory body text.
Continuation Contract: This Skill output is only Front Pipeline step 1. After the main agent receives the Intent Card, if confidence >= 0.75 and ambiguities is empty, it must continue to archi-context-fetch, then load the protocol pointed to by recommended_next_action; do not treat the Intent Card as the final reply.
requires_user_confirmation is a later protocol Gate marker, not a Front Pipeline stop marker. Except for safety cases such as delete, overwrite, dependency install, pack restore, or cross-task global change, routing Intent Cards should keep requires_user_confirmation: false.
{
"intent_card_version": 1,
"raw_user_message": "<Original summary, preserving key verbs and objects>",
"normalized_goal": "<One sentence explaining what user really wants to achieve>",
"intent_type": "init | plan | change | code | review | remove | ui | ref | help | answer | unknown",
"command": "/archi.init | /archi.plan | /archi.change | /archi.code | /archi.review | /archi.remove | /archi.ui | /archi.ref | /archi.help | none",
"subprotocol": "start | inherit | recover | decompose | detail | fix | edit | revise | task | project | map | add | list | update | remove | none",
"target": {
"task_id": null,
"files": [],
"refs": [],
"feature_area": null
},
"scope": "single-task | multi-task | global | project-setup | docs-only | code-only | read-only | unknown",
"operation_kind": "read | write-docs | write-code | delete | overwrite | command-run | none",
"requires_user_confirmation": false,
"confidence": 0.0,
"ambiguities": [],
"routing_reason": ["<Matched semantic signal>"],
"recommended_next_action": "<Protocol to load next or question to ask>"
}
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.
- 9d ago First seen · 145 lines · 43 tokens per session scan A 1decbc3d99ea
archi-intent-normalizer is a skill published in the GitHub repository JiuNian3219/architext (14 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,634 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 2026-08-30.
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.
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.