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-constitution-draftgit 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-constitution-draft)<a href="https://agentmods.dev/skills/jiunian3219/architext/archi-constitution-draft"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-constitution-draft/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-constitution-draft"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-constitution-draft.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 | $0.00042 | $0.02305 |
| Opus 5 | $0.00021 | $0.01153 |
| Sonnet 5 | $0.00008 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
archi-constitution-draft 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 — 142 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 via
[[SUBAGENT]]/[[NO-SUBAGENT]]in/archi.*protocols. - Execution context: When subagent supported must execute in independent subagent/independent context; only downgrade to inline Skill when no subagent.
- Boundary: Only return protocol-required structured artifacts, subsequent write, confirm and signoff handled by calling protocol.
Design Principles
- Self-Contained Rules: Data source matrix and generation rules embedded in this SKILL.md's step_1_data_source, as single source of truth
- Two-Phase Generation: First generate all file content in memory → Unified write; generation phase failure does not write any file
- Summary Only: Do not report reasoning details during generation to main agent, only return write list, AI completion items, ambiguity items
- Conditional Generation: Specific files not matching feature_tags (e.g. non-ui project doesn't generate design_tokens.json) skip directly
Execution Phases
step_1_data_source Data Source and Rules
Context Prerequisites:
brief_data(optional, archi-brief-scan output)code_analysis(optional, archi-code-survey output)feature_tags(architext.json, always present)
Execute per matrix three columns below based on current data combination.
General Rules:
- No template placeholders — All example text must be replaced
- AI completion must mark
(AI Recommended — suggest user review)+ reason - Priority: User filled > Brief determined > Code facts > AI recommended; when higher priority exists, do not override lower
- feature_tags conditional generation: Only generate specific files matching this project's feature_tags
Data Source Matrix:
| Target File | When has brief_data | When has code_analysis | When both |
|---|---|---|---|
vision.md |
brief_data.identity / targetUsers / successMetrics / boundaries / references | README + project config inference (mark low confidence) | Brief priority, code fills missing fields |
Rules file tech_stack |
brief_data.techStack (filled items directly; empty items AI recommended) | Dependency list + config files + code pattern recognition | Brief determined > Code facts > AI recommended |
tech_stack Section 9 |
Generate default strategy by feature_tags (see §3) | Recognize existing error handling/data flow patterns from code | Code facts priority (existing conventions must be respected) |
Rules file 90_custom_rules |
Rule content from brief_data.supplementaryNotes | eslint/prettier/editorconfig + team conventions recognized from code | Merge (dedupe, mark conflicts) |
roadmap.json |
brief_data.coreTasks → phase-1/2 (call archi-decompose-roadmap) | Code feature modules → phase-0 LEG-xx (status=done, tag=Legacy) | phase-0 from code, phase-1/2 from Brief |
dictionary.json |
brief_data full text term extraction | Code naming + comment extraction | Merge dedupe |
error_codes.json |
Pre-define core error codes by coreTasks | Extract from throw/Error definitions in code | Code facts priority |
env_registry.json |
Environment variables implied by brief_data.techStack | process.env / os.Getenv / os.environ references in code |
Code facts priority |
map.json |
techStack architecture pattern pre-register directory skeleton; logicalTopology/journeys empty | Actual directories + import chains + user journeys | Code facts priority (map is essentially fact recording) |
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 · 142 lines · 42 tokens per session scan A 6e972bdac301
archi-constitution-draft is a skill published in the GitHub repository JiuNian3219/architext (14 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 2,305 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.