wiki-source-code

A set of TypeScript coding rules for an LLM Wiki agent project, including its Node.js runtime, command-line tools, and source layout.

In plain words
What is it for?
Use it when adding or changing TypeScript code so imports, model configuration, project structure, and quality checks follow the repository's conventions.
Why use it?
It keeps shared logic, workflow code, and command-line code organized and sets checks for types, linting, formatting, and strict typing.

Cursor rule for Codex

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 rules/regexp-lin/llm-wiki-agent/wiki-source-code
Clone the repo
git clone --depth 1 https://github.com/regexp-lin/llm-wiki-agent

Made for: Codex.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 284 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 $0.00000 $0.00284
Opus 5 $0.00000 $0.00142
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash a835201266a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-source-code 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.

.agents/rules/wiki-source-code.mdc · 36 lines

What it actually says

TypeScript Source Code Conventions

Project Stack

  • Runtime: Node.js 22.16.0 + TypeScript (ESM)
  • LLM: Anthropic Claude via @anthropic-ai/sdk
  • Graph: graphology + graphology-communities-louvain + vis.js
  • CLI: commander
  • Package manager: pnpm

Architecture

src/
├── shared/        # Shared modules (types, constants, utils)
├── workflows/     # Four core workflows (ingest, query, lint, graph)
└── cli/           # CLI entry points (thin wrappers over workflows)
  • Business logic lives in src/workflows/, CLI parsing lives in src/cli/.
  • Shared utilities in src/shared/ — do not duplicate code across workflows.
  • All imports use .js extension (ESM requirement).
  • Model names are centralized in src/shared/constants.ts.

Quality

  • Run pnpm typecheck before committing.
  • Run pnpm lint and pnpm format to check code standards.
  • TypeScript strict mode is enabled — no any types unless absolutely necessary.
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 · 36 lines · 0 tokens per session scan A a835201266a8

Subscribe to this mod's changes

wiki-source-code is a cursor rule published in the GitHub repository regexp-lin/llm-wiki-agent (15 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 284 tokens. 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.