harmonica-chat: Instructions file for Claude Code

CLAUDE.md

harmonica-chat CLAUDE.md is an instructions file for Claude Code from harmonicabot/harmonica-chat. It costs 2,726 tokens per session, scanned A, original, MIT.

Project instructions for Harmonica Chat, a Claude Code skill for creating and managing group deliberation sessions.

In plain words
What is it for?
Working on Harmonica Chat's commands, session design, lifecycle, invitations, and documentation.
Why use it?
They explain the repository structure, required service, and design rules so contributors can change the skill consistently.

Instructions file for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is harmonicabot/harmonica-chat's own configuration. It tells Claude Code how to work on harmonica-chat 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 harmonica-chat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to harmonicabot/harmonica-chat. 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/harmonicabot/harmonica-chat/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/harmonicabot/harmonica-chat

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 harmonica-chat CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/harmonicabot/harmonica-chat/claude-md/github.svg)](https://agentmods.dev/instructions/harmonicabot/harmonica-chat/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/harmonicabot/harmonica-chat/claude-md"><img src="https://agentmods.dev/badge/instructions/harmonicabot/harmonica-chat/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.

agentmods 80×15 button for harmonica-chat CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/harmonicabot/harmonica-chat/claude-md"><img src="https://agentmods.dev/badge/instructions/harmonicabot/harmonica-chat/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,726 This file is loaded in full into every session.
When invoked 2,726 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02726 $0.02726
Opus 5.5 $0.01090 $0.01090
Sonnet 5.5 $0.00545 $0.00545
Haiku 4.5 $0.00273 $0.00273

Measured 7d ago against content hash 6047c68c3492, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harmonica-chat CLAUDE.md scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Version auto-update.** The version comment near the top of SKILL.md is `<!-- harmonica-chat vX.Y.Z -->`. Guided design checks GitHub and notifies users if outdated; every Harmonica MCP call includes this installed vers
CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

harmonica-chat is a Claude Code skill (/harmonica-chat) that designs, creates, and manages Harmonica deliberation sessions. It's distributed as a thin entry router (SKILL.md) plus lazy-loaded reference files (reference/*.md) that users install to ~/.claude/skills/harmonica-chat/.

The skill uses Harmonica MCP for API access. New installs default to Pro's hosted endpoint, https://app.harmonica.chat/api/mcp/mcp. The harmonica-mcp npm package remains a maintenance-only compatibility option for stdio and self-hosted REST APIs. Preserve existing registrations when updating the skill; do not silently migrate them. Installers store an environment-variable reference for new hosted connections, so the key must remain in the environment that launches the agent.

Repository Structure

  • SKILL.md — Entry router (~120 lines). Frontmatter, prerequisites, session design laws, argument routing, commands menu. This file MUST stay thin; subcommand logic lives in reference/.
  • reference/ — subcommand reference files. Loaded on demand by the entry router.
    • design.md — Mode 1: guided session design, 14 steps
    • accelerated.md — Mode 2: topic-upfront flow + project-aware creation
    • status.md, check.md, summary.md, edit.md, review.md, follow-up.md — lifecycle commands
    • invitation.md — post-creation invitation flow (join URL, draft message, community feed)
    • expertise.md — soft-nudge session design heuristics (goal quality, context calibration, cross-pollination, critical questions)
    • onboarding.md — hosted-MCP continuation for a saved Shape C flow; ordinary local-npm sessions stay on existing routes

Templates are NOT in reference/ — they're fetched at runtime via mcp__harmonica__list_templates (harmonica-mcp ≥ 0.11.0). The Harmonica admin panel is the single source of truth; the skill never hardcodes a template list. See HAR-1227.

  • install.sh / install.ps1 — One-line installers. Download SKILL.md + all reference files. v3.0.0+ also migrates the legacy v2.x slash-command install (removes ~/.claude/commands/harmonica-chat.md if present).
  • docs/plans/ — Design docs for major rewrites (reference only, not part of the product).

Read the full file on GitHub · 95 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.

  1. 7d ago Changed · +12 lines · +139 tokens per session 6047c68c3492
  2. 29d ago Changed · +4 lines · +558 tokens per session 1f50527a625f
  3. 1mo ago Changed · +10 lines · +521 tokens per session f17a38b9798d
  4. 1mo ago Changed · +65 tokens per session b0d42f6b691f
  5. 2mo ago First seen · 69 lines · 1,443 tokens per session scan A 3a7106c1df86

Subscribe to this mod's changes

harmonica-chat CLAUDE.md is an instructions file published in the GitHub repository harmonicabot/harmonica-chat (2 stars, last pushed 7d ago), licensed MIT. It adds 2,726 tokens to every session, about $0.0109 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

harmonica-chat CLAUDE.md compared with instructions from other repositories

harmonica-chat CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
harmonica-chat CLAUDE.mdharmonicabot/harmonica-chatInstructions file27d agoMITA2,726Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281kyesterdayMITA4,335Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot