cli-forge-schema

A guide for creating Mermaid diagrams, which are text-based diagrams that can render in GitHub and other supported tools.

In plain words
What is it for?
Making flowcharts, sequence diagrams, architecture diagrams, data models, state machines, timelines, and other project diagrams.
Why use it?
It helps represent code or system relationships clearly while avoiding diagram syntax that GitHub cannot display.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/destynova2/cli-code-skills/cli-forge-schema
Any agent
npx skills add Destynova2/cli-code-skills --skill cli-forge-schema
Clone the repo
git clone --depth 1 https://github.com/Destynova2/cli-code-skills

Made for: Claude Code, Codex.

Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00199 $0.02664
Opus 5 $0.00100 $0.01332
Sonnet 5 $0.00040 $0.00533
Haiku 4.5 $0.00020 $0.00266

Measured 2d ago against content hash 799a270406be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-forge-schema 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 2d 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.

cli-forge-schema/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimization: This skill uses on-demand loading. Heavy content lives in references/ and is loaded only when needed.

Language rule: Skill instructions are written in English. When generating user-facing output, detect the project's primary language (from README, comments, docs, commit messages) and produce labels, titles, and annotations in that language. If the project is bilingual, ask the user which language to use before proceeding.

Schema Forge — Clear Diagrams, Zero Syntax Errors

Generate professional, GitHub-compatible Mermaid diagrams that are readable first, pretty second.

Core Philosophy

  1. Clarity over completeness — a diagram that shows too much shows nothing. If it's complex, split it
  2. Right tool for the job — pick the diagram type that makes the data obvious, not the one that looks fancy
  3. GitHub-first — every diagram must render on GitHub without errors. No FontAwesome, no click events, no exotic features
  4. UX ergonomics — treat diagrams like UI: if a user needs more than 5 seconds to understand the flow, redesign it
  5. Truth over aspiration — a diagram must reflect what EXISTS in the code, not what someone hopes to build. Stale diagrams are worse than no diagrams
  6. Gotchas — read ../gotchas.md before producing output to avoid known mistakes

Operating Modes

This skill operates in three modes, detected from the user's input:

Mode A — Single Diagram

The user describes something specific to visualize. Generate one diagram.

Trigger: text description, broken Mermaid, table to convert, specific request.

Mode B — Doc Scan & Convert

The user points at a directory or says "scan", "audit docs", "make visual". The skill crawls documentation files and converts everything that would be genuinely more readable as Mermaid.

Trigger: path to a directory, "scan docs", "convert everything", "make docs visual".

Mode C — Project Schema

The user wants a diagram of the current project (architecture, module structure, data flow). The skill reads the actual codebase to generate accurate diagrams.

Read the full file on GitHub · 242 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 242 lines · 199 tokens per session scan A 799a270406be

Subscribe to this mod's changes

cli-forge-schema is a skill published in the GitHub repository Destynova2/cli-code-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 199 tokens to every session and 2,664 once invoked, about $0.0010 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 2026-08-31.