Borrowing it
Nothing to install: this file belongs to alfadur7/llm-wiki-newsroom. 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/alfadur7/llm-wiki-newsroom/main/CLAUDE.mdgit clone --depth 1 https://github.com/alfadur7/llm-wiki-newsroomWrote 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/instructions/alfadur7/llm-wiki-newsroom/claude-md)<a href="https://agentmods.dev/instructions/alfadur7/llm-wiki-newsroom/claude-md"><img src="https://agentmods.dev/badge/instructions/alfadur7/llm-wiki-newsroom/claude-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/instructions/alfadur7/llm-wiki-newsroom/claude-md"><img src="https://agentmods.dev/badge/instructions/alfadur7/llm-wiki-newsroom/claude-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 | $0.04858 | $0.04858 |
| Opus 5.5 | $0.01943 | $0.01943 |
| Sonnet 5.5 | $0.00972 | $0.00972 |
| Haiku 4.5 | $0.00486 | $0.00486 |
Grade A, and why
llm-wiki-newsroom CLAUDE.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 1mo 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki Newsroom
This wiki is an English-native knowledge base maintained by Claude Code; the example corpus shipped here maps the debate over what "open source" means for AI, but the framework is domain-agnostic. It requires no external API keys — the Python scripts under tools/ run entirely locally. When the user makes a request in natural language or runs a slash command, these instructions route the work to the appropriate one of the five roles.
Roles
This project operates as a five-role multi-agent system modeled on the staff of a Korean newsroom.
| Role | Essence |
|---|---|
| Editor-in-Chief | Meta layer outside the matrix — entry, routing, gating, escalation, logging |
| Reporter | Writes L2-1 / L2-2 stubs + broad external exploration (breadth-first parallel) |
| Columnist | Writes L2-2 full / L2-3 / L2-4 (integrating its own GROUND, deep sequential) |
| Desk1 | Qualitative review of L2-2 full hub·stub / L2-3 / L2-4, plus L2-1 on its sub-trigger (the areas the Rubric does not capture — scope per desk.md) — the pre-publish gate |
| Copy Editor | Deterministic quantitative checks across all Layers (tools/lint.py) |
Per-role capabilities, prompts, and risk mitigations: .claude/agents/ is the SoT.
Universal Cycle
Every workflow in this project maps onto a four-stage cycle — ingest, query, lint, and reground all share the same skeleton.
| Stage | Essence | Owner |
|---|---|---|
| GROUND | Read the relevant SoT (observe) | Reporter / Columnist read directly from their own context (avoiding the telephone game) |
| APPLY | Write/edit following the observed pattern | Reporter / Columnist write the EDITOR block (preserving the AUTO block) |
| VERIFY | Confirm lint/tools PASS (verification) | Copy Editor (quantitative) → Desk (qualitative — scope per the desk.md matrix), divided |
| ADAPT | On VERIFY failure, return to GROUND | Reporter / Columnist (no qualitative self-review) |
Footnotes
-
"Desk" is the newsroom desk — the senior editor who reviews a piece for quality and judgment before it runs (as in "copy desk" / "news desk"). Here it is the pre-publish qualitative-review gate. The five roles are modeled on a newspaper newsroom; the agent and its SoT file are both named
desk. ↩
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.
- 1mo ago Changed · -4 lines · -58 tokens per session 91a0d724a81b
- 1mo ago Changed · +76 tokens per session 5c00cc8c44f9
- 1mo ago Changed · +96 tokens per session 8ba0efa83044
- 1mo ago Changed · -2 tokens per session 1e9571bba7dc
- 1mo ago First seen · 218 lines · 4,746 tokens per session scan A e3ef05ab88bf
llm-wiki-newsroom CLAUDE.md is an instructions file published in the GitHub repository alfadur7/llm-wiki-newsroom (173 stars, last pushed 14d ago), licensed MIT. It adds 4,858 tokens to every session, about $0.0194 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.