DanNet: Instructions file for Claude Code

CLAUDE.md

DanNet CLAUDE.md is an instructions file for Claude Code from kuhumcst/DanNet. It costs 576 tokens per session, scanned A, original, MIT.

Repository instructions for DanNet, a Danish WordNet implemented in Clojure, a functional programming language. They favor small edits and testing through the project's interactive programming environment, called a REPL.

In plain words
What is it for?
Use it when changing Clojure or ClojureScript code, reloading namespaces after edits, testing functions in the REPL, or debugging frontend behavior through the browser REPL.
Why use it?
They reduce unnecessary refactoring and make testing fit the project's functional, REPL-based workflow. They also require reporting unusual behavior promptly and using live browser debugging for frontend issues.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kuhumcst/DanNet's own configuration. It tells Claude Code how to work on DanNet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DanNet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kuhumcst/DanNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kuhumcst/DanNet/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kuhumcst/DanNet

Made for: Claude Code.

Wrote 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.

agentmods badge for DanNet CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kuhumcst/dannet/claude-md.svg)](https://agentmods.dev/instructions/kuhumcst/dannet/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kuhumcst/dannet/claude-md"><img src="https://agentmods.dev/badge/instructions/kuhumcst/dannet/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 576 This file is loaded in full into every session.
When invoked 576 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00576 $0.00576
Opus 5 $0.00288 $0.00288
Sonnet 5 $0.00115 $0.00115
Haiku 4.5 $0.00058 $0.00058

Measured 2d ago against content hash 84cf2312edff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

DanNet 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 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.

CLAUDE.md · 20 lines

What it actually says

  • Clojure is a FUNCTIONAL programming language.
    • i.e. I expect you to do to REPL-based development in a FUNCTIONAL style.
      • So when testing newly developed code, please just do a few relevant function calls in the REPL.
  • Be surgical in your edits.
    • I generally favour clean and lean git diffs over large refactors of the namespace(s).
  • IMPORTANT: if you encounter something UNUSUAL (e.g. weird output or unexpected errors), report back immediately to me!
    • Don't go on a longer tangent trying to analyze an unexpected error yourself (unless it is trivial to do so).
  • You may start or restart the web service via the REPL (e.g. (service/restart)) when the task calls for it — e.g. when setting up the environment or when a change genuinely requires a restart.
    • For routine fixes, still prefer testing in an isolated way using the REPL rather than restarting.
  • After editing CLJ or CLJC files, reload the affected namespaces using (require '[namespace] :reload) so the changes take effect in the running REPL.
  • For frontend-only bugs (hydration errors, CLJS/CLJ differences, CSS/layout issues), debug in the LIVE BROWSER via the shadow-cljs nREPL rather than guessing from source — follow the browser-repl-debug skill (it loads on demand).
  • REPL access: use the clj-nrepl-eval command to evaluate Clojure code via nREPL.
    • Discover running nREPL servers with clj-nrepl-eval --discover-ports.
    • Evaluate with clj-nrepl-eval -p <port> "<clojure-code>" (JVM nREPL: port 7888 via the :nrepl alias; shadow-cljs runs its own auto-discoverable nREPL port).
    • REPL sessions persist per port: namespaces and state are maintained between evaluations.
  • When writing, editing, or reviewing Clojure code, follow the clojure-style skill (it loads on demand).
  • Database (re)builds:
    • bootstrap/other/ holds manually curated source files that are NOT fetched automatically; the COR files (cor*.tsv, *.cordiff, cor.sem.*.tsv) can be re-downloaded from https://ordregister.dk/files/ if missing.
    • If a DB build fails partway, delete the half-built db/tdb2/<db-name> directory (the path is in the build error's :data) before restarting — ->dannet only checks that the directory exists and will otherwise silently reuse the incomplete database ("Skipping build").
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 Changed · +3 lines · +158 tokens per session 84cf2312edff
  2. 7d ago First seen · 17 lines · 418 tokens per session scan A b2303048e38e

Subscribe to this mod's changes

DanNet CLAUDE.md is an instructions file published in the GitHub repository kuhumcst/DanNet (29 stars, last pushed 3d ago), licensed MIT. It adds 576 tokens to every session, about $0.0029 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens