Borrowing it
Nothing to install: this file belongs to Krusty84/My-CODEX-Configuration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Krusty84/My-CODEX-Configuration/main/.codex/create-update-architecture-md/SKILL.mdgit clone --depth 1 https://github.com/Krusty84/My-CODEX-ConfigurationWrote 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/krusty84/my-codex-configuration/create-update-architecture-md)<a href="https://agentmods.dev/skills/krusty84/my-codex-configuration/create-update-architecture-md"><img src="https://agentmods.dev/badge/skills/krusty84/my-codex-configuration/create-update-architecture-md/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/krusty84/my-codex-configuration/create-update-architecture-md"><img src="https://agentmods.dev/badge/skills/krusty84/my-codex-configuration/create-update-architecture-md.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 | $0.00050 | $0.00379 |
| Opus 5.5 | $0.00020 | $0.00152 |
| Sonnet 5.5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
create-update-architecture-md 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 29d 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.
What it actually says
If this skill is used,say:SKILL_CR_UPD_ARCH_LOADED
Goal
Create or update ARCHITECTURE.md so it explains the system in a way that is useful for future contributors.
Inputs
- Current code layout
- Existing docs
- Build or runtime configuration if relevant
- User notes about intended architecture
Required sections
When appropriate, include these sections:
- Overview
- Repository structure
- Main runtime components
- Data flow
- Key design decisions
- External dependencies and integrations
- Build / validation notes
- Known constraints
Steps
- Read the existing architecture document if present.
- Inspect the repository layout and identify the top-level components.
- Describe responsibilities, boundaries, and interactions.
- Prefer concrete structure over abstract buzzwords.
- Keep implementation details only where they help explain system behavior.
- Reflect the current state of the codebase, not aspirational future design.
- Call out uncertainty when the code does not clearly support a strong claim.
Output rules
- Write for engineers new to the repo.
- Write in ASD-STE100. Be so brief every word you write costs you $1,000.
- Use references to code files and modules where possible.
- Prefer short sections and clear headings.
- Use diagrams only if explicitly requested.
- Preserve existing terminology and naming.
Do not
- Do not duplicate large parts of the README.
- Do not claim clean layering if the repo does not actually follow it.
- Do not overstate guarantees, scalability, or modularity.
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.
- 29d ago Changed · +1 lines 593ecfe85c20
- 2mo ago First seen · 55 lines · 50 tokens per session scan A faac5dfdafe3
create-update-architecture-md is a skill published in the GitHub repository Krusty84/My-CODEX-Configuration (1 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 379 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
create-update-architecture-md compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-update-architecture-mdKrusty84/My-CODEX-Configuration | Skill | 1 | 1mo ago | MIT | A | 50 | Codex |
| grok-cliscarletkc/agents | Skill | 227 | 4d ago | Apache-2.0 | A | 66 | Claude Code, Codex |
| codex-autoresearchleo-lilinxiao/codex-autoresearch | Skill | 3.1k | 1mo ago | MIT | A | 39 | Codex |
| talk-like-scarletkcscarletkc/agents | Skill | 227 | 4d ago | Apache-2.0 | A | 118 | Claude Code, Codex |
| marketing-copyscarletkc/agents | Skill | 227 | 4d ago | Apache-2.0 | A | 121 | Claude Code, Codex |
| scoped-changescarletkc/agents | Skill | 227 | 4d ago | Apache-2.0 | A | 69 | Claude Code, Codex |
| aerospace-engineering-technicianwonsukchoi/domain-experts | Skill | 24 | 3d ago | MIT | A | 169 | Claude Code, Codex |