Borrowing it
Nothing to install: this file belongs to vonzelle-vzt/herdr-extensions. 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/vonzelle-vzt/herdr-extensions/main/CLAUDE.mdgit clone --depth 1 https://github.com/vonzelle-vzt/herdr-extensionsWrote 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/vonzelle-vzt/herdr-extensions/claude-md)<a href="https://agentmods.dev/instructions/vonzelle-vzt/herdr-extensions/claude-md"><img src="https://agentmods.dev/badge/instructions/vonzelle-vzt/herdr-extensions/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/vonzelle-vzt/herdr-extensions/claude-md"><img src="https://agentmods.dev/badge/instructions/vonzelle-vzt/herdr-extensions/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 | $0.02330 | $0.02330 |
| Opus 5 | $0.01165 | $0.01165 |
| Sonnet 5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
herdr-extensions 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 10d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — herdr-extensions
Project guidance for Claude Code. Read this before changing anything here; it records the failure modes that are invisible from the code alone.
What this is
An installer, not a framework. It makes herdr behave like a tiny VS Code by writing a plugin manifest, some scripts, and a marker-delimited block of keybindings. There is no plugin manager and no config DSL, deliberately. Read README.md for the product and SPEC.md for every design decision and the reason behind it — SPEC.md is the authority, and each numbered decision is a bug this package prevents.
bin/herdr-extensions is stdlib-only Python targeting 3.9 (what macOS ships), so there is no
tomllib. Config edits are marker-delimited text splices, never TOML round-trips — that is also why
your comments and settings survive.
Repository map
bin/herdr-extensions the whole CLI: install / uninstall / doctor / skin
plugin/herdr-plugin.toml herdr plugin manifest — a TEMPLATE, rendered at install time
plugin/open-panel.sh launcher: decides open/focus/close, project scope, and panel geometry
plugin/resize-pane.sh one-keypress divider nudge
plugin/image-paste.sh stage a clipboard image and type its path to the agent
libexec/<panel> one script per panel: problems search todo blame markdown tests debug preview
libexec/herdr-fmt formatter resolver used for format-on-save
skins/*.toml VS Code colour schemes for herdr itself
tests/ the oracles; see "Verification" below
🔴 The five things that fail silently
Every one of these has actually shipped broken. None produces an error message.
1. Pane commands run under launchd's PATH. The herdr server is started by launchd, so it execs
plugin panes and actions with PATH=/usr/bin:/bin:/usr/sbin:/sbin. Neither /opt/homebrew/bin nor
/usr/local/bin nor ~/.local/bin is on it. A bare spiceedit, lazygit, chafa or rg never
resolves and the action does nothing at all. Every external binary is therefore an @@TEMPLATE@@
rendered to an absolute path by render_plugin(). Worth knowing: on many machines rg is a shell
function, so anything that execves it fails even though it works when you type it.
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.
- 10d ago First seen · 149 lines · 2,330 tokens per session scan A 95962efeb1cc
herdr-extensions CLAUDE.md is an instructions file published in the GitHub repository vonzelle-vzt/herdr-extensions (6 stars, last pushed 1mo ago), licensed MIT. It adds 2,330 tokens to every session, about $0.0117 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.
Other instructions, from other repositories
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.
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.
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).
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.
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).
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.