What is herdmates CLAUDE.md?

A project instruction file for Herdmates, a system for coordinating Claude Code teammates and showing their work in panes and a shared board. It explains the project's context, terminology, decisions, and required reading order.

Use it when working on Herdmates code, especially its teammate panes, agent board, focus pane, and related project documentation.

It gives the coding agent the background and rules needed to work consistently in the repository. It also prevents older design decisions from being changed without review.

How caioniehues/herdmates configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to caioniehues/herdmates. 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/caioniehues/herdmates/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/caioniehues/herdmates

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/caioniehues/herdmates/claude-md/github.svg)](https://agentmods.dev/instructions/caioniehues/herdmates/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/caioniehues/herdmates/claude-md"><img src="https://agentmods.dev/badge/instructions/caioniehues/herdmates/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/caioniehues/herdmates/claude-md"><img src="https://agentmods.dev/badge/instructions/caioniehues/herdmates/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,177 This file is loaded in full into every session.

When invoked 2,177 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.

Model	Per session	Once invoked
Fable 5.1	$0.02177	$0.02177
Opus 5	$0.01089	$0.01089
Sonnet 5	$0.00435	$0.00435
Haiku 4.5	$0.00218	$0.00218

Measured 9d ago against content hash 94ebe323eb74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

herdmates 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 9d 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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — project context for Claude Code

Herdmates (pivoted from herdr-agent-team, ADR-0012, 2026-07-16): Claude Code teammates, native in herdr. Three surfaces: shim ("teammux" — fake tmux translating to herdr CLI so native split-pane teammates land as real herdr panes), agent board (sidebar tokens, TUI plugin pane later), focus pane (human focus: one next action + decision queue). We do NOT build our own orchestration — native Claude Code agent teams own spawn/messaging/lifecycle; we host + observe.

Read in this order

HANDOFF.md — current state + exact NEXT steps (foundation checklist).
docs/adr/0012-pivot-to-herdmates.md — the pivot: full context, verified facts with citations, every decision, spike kill criteria.
docs/adr/0001–0011 — locked decisions with the why. 0002/0003/0006/ 0007/0008/0009 describe the frozen legacy surface. No silent relitigating; new evidence → new ADR, ask Caio first.
CONTEXT.md — vocabulary. Pivot terms first (herdmates, native team, lead, teammate, teammate mode, shim, recon spike, team files, agent board, focus pane, focus file, atomizer, plugin pane vs popup pane, sidebar token); legacy terms below them.

Hard rules

Repo public (herdr-plugin marketplace topic). Pushes to main are releases: gate every push (fmt/clippy/tests), bump manifest version on behavior change, tag releases. No push without Caio's ask.
The herdr CLI (via HERDR_BIN_PATH) is the entire plugin API — no SDK. Ground truth for verbs: herdr <cmd> --help and docs/herdr-api-schema.snapshot.json (re-snapshot + diff after any herdr update).
Pane cwd is set at pane creation (--cwd), never via cd in prompt text (ADR-0004 — split-brain trap).
Never re-implement native-team features (spawn, mailboxes, membership, lifecycle) — read the documented team files instead (~/.claude/teams/{team}/config.json, inboxes/*.json).
Shim work is gated on the recon spike verdict (ADR-0012); do not build the translator before the verb inventory exists.
Boards/focus pane must not require the shim — they work over in-process teams in any terminal.

Read the full file on GitHub · 167 lines

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.

9d ago First seen · 167 lines · 2,177 tokens per session scan A 94ebe323eb74

Subscribe to this mod's changes

herdmates CLAUDE.md is an instructions file published in the GitHub repository caioniehues/herdmates (24 stars, last pushed 19d ago), licensed MIT. It adds 2,177 tokens to every session, about $0.0109 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.

Claude Code agent-teams herdr-plugin tui

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

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 · 5,153 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

herdmates: Instructions file for Claude Code