agentmods.dev

converse: Instructions file for Claude Code

CLAUDE.md

converse CLAUDE.md is an instructions file for Claude Code from FallDownTheSystem/converse. It costs 4,338 tokens per session, scanned A, original, MIT.

Development instructions for Converse, a Node.js MCP server whose chat tool can run models independently, compare their answers, or let them build on a shared conversation.

In plain words
What is it for?
Use them when installing, developing, testing, or extending the Converse MCP server.
Why use it?
They document the project layout, supported conversation modes, required package manager, and common development commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Codex.

This is FallDownTheSystem/converse's own configuration. It tells Claude Code how to work on converse 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 converse configures →

not rated 2repo changed 14d ago A scan 4,338 tokens original MIT
View source ↗ FallDownTheSystem/converse
Reuse

Borrowing it

Nothing to install: this file belongs to FallDownTheSystem/converse. 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/FallDownTheSystem/converse/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/FallDownTheSystem/converse

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 converse CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/falldownthesystem/converse/claude-md"><img src="https://agentmods.dev/badge/instructions/falldownthesystem/converse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,338 This file is loaded in full into every session.
When invoked 4,338 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 $0.04338 $0.04338
Opus 5.5 $0.01735 $0.01735
Sonnet 5.5 $0.00868 $0.00868
Haiku 4.5 $0.00434 $0.00434

Measured 14d ago against content hash cdf86aa2f838, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

converse 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 14d 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 · 430 lines

How it starts

The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Development Guide for Converse MCP Server

This repository contains the Converse MCP Server - a functional Node.js implementation of an MCP server.

Repository Structure

  • src/ - Main source code for the Converse MCP Server
  • docs/ - Complete documentation (API, Architecture, Examples)
  • tests/ - Comprehensive test suite (unit, integration, e2e)
  • scripts/ - Development and build scripts
  • examples/ - Usage examples and sample configurations
  • bin/ - Executable binaries for CLI usage

Converse MCP Server (Node.js)

The Converse MCP Server follows a functional architecture with a single unified chat tool that takes a mode parameter:

  1. chat mode - 1..N models answer independently in parallel
  2. consensus mode - ≥2 models answer in parallel, then refine via cross-feedback
  3. roundtable mode - models answer sequentially, each building on the running transcript

Development Setup

IMPORTANT: This project uses pnpm, not npm.

# Install dependencies (use pnpm, NOT npm)
pnpm install

# Start development server
pnpm run dev

# Run tests
pnpm test

For detailed implementation guidance, see:

  • docs/API.md - Complete API reference
  • docs/ARCHITECTURE.md - System architecture and design principles
  • docs/EXAMPLES.md - Usage examples and patterns

Release & CI Automation

This repo is fully automated for releases via release-please. Do not manually bump versions in package.json, manually run npm publish, or manually edit the top of CHANGELOG.md — the automation owns these.

How releases work

  • Every push to main with a user-facing commit triggers a release. release-please skips pushes whose commits are all hidden types (ci:, chore:, docs:, etc.) with "No user facing commits found — skipping"; force one of these with a Release-As: footer if you need to. Dependabot auto-merges explicitly dispatch the same workflow after merge so dependency bumps still publish a patch release (always-bump-patch strategy). Workflow: .github/workflows/release.yml.
  • The flow in a single workflow run (~50s):
    1. release-please opens (or updates) a "chore(main): release X.Y.Z" PR with version bump + CHANGELOG.md entry.
    2. Workflow auto-merges that PR with gh pr merge --squash.
    3. release-please runs again, sees the just-merged release PR, tags vX.Y.Z, creates a GitHub Release.
    4. Workflow runs pnpm install --frozen-lockfile + lint + typecheck + test:unit, upgrades npm (npm install -g npm@latest), then npm publish --access public.
  • Branch protection on main is off — direct pushes are allowed and intentional, since the automation needs to push the auto-merge commit.
  • Publishing uses npm Trusted Publishing (OIDC) — no NPM_TOKEN secret. The job's id-token: write permission + a trusted publisher configured on npmjs.com (org FallDownTheSystem, repo converse, workflow release.yml) authenticate the publish, and provenance is generated automatically. Trusted Publishing requires npm >= 11.5.1, which is why the workflow upgrades npm before publishing.

Read the full file on GitHub · 430 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. 14d ago Changed · +3 lines · +193 tokens per session cdf86aa2f838
  2. 22d ago Changed · +16 tokens per session d00c457c30a2
  3. 1mo ago Changed · +101 tokens per session db8675003027
  4. 1mo ago Changed · +6 lines · +161 tokens per session 27a4b0aded4c
  5. 2mo ago First seen · 421 lines · 3,867 tokens per session scan A 7ca5107359a8

Subscribe to this mod's changes

converse CLAUDE.md is an instructions file published in the GitHub repository FallDownTheSystem/converse (2 stars, last pushed yesterday), licensed MIT. It adds 4,338 tokens to every session, about $0.0174 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 2026-08-31.

LLMaimcpmcp-servermodelcontextprotocolprompt
Related

converse CLAUDE.md compared with instructions from other repositories

converse CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
converse CLAUDE.mdFallDownTheSystem/converseInstructions file2yesterdayMITA4,338Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode