launch-swarm: Instructions file for Claude Code

CLAUDE.md

launch-swarm CLAUDE.md is an instructions file for Claude Code from harshmoney123/launch-swarm. It costs 1,237 tokens per session, scanned A, original, MIT.

Repository instructions for Launch Swarm, a multi-agent development workflow. They define branching, pull-request review, planning, tests, protected branches, and project-specific private settings.

In plain words
What is it for?
Use them when starting work, selecting a branch, creating or reviewing pull requests, coordinating agents, and following the project's test-first workflow.
Why use it?
They reduce conflicts between agents and make the review and merge process predictable; TDD means writing failing tests before the code that makes them pass.

Instructions file for Claude Code

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

This is harshmoney123/launch-swarm's own configuration. It tells Claude Code how to work on launch-swarm 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 launch-swarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to harshmoney123/launch-swarm. 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/harshmoney123/launch-swarm/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/harshmoney123/launch-swarm

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 launch-swarm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/harshmoney123/launch-swarm/claude-md/github.svg)](https://agentmods.dev/instructions/harshmoney123/launch-swarm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/harshmoney123/launch-swarm/claude-md"><img src="https://agentmods.dev/badge/instructions/harshmoney123/launch-swarm/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 launch-swarm CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/harshmoney123/launch-swarm/claude-md"><img src="https://agentmods.dev/badge/instructions/harshmoney123/launch-swarm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,237 This file is loaded in full into every session.
When invoked 1,237 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 $0.01237 $0.01237
Opus 5 $0.00619 $0.00619
Sonnet 5 $0.00247 $0.00247
Haiku 4.5 $0.00124 $0.00124

Measured 9d ago against content hash 5f1ae20852d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

launch-swarm 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Global Development Rules

IMPORTANT: Read .claude/.private/overrides.md first — it maps all YOUR_ placeholders in these rules to real project values. Read .claude/.private/reference-ids.md for all real IDs.*

Project-level CLAUDE.md takes precedence on conflicts.

Git Workflow

At session start, run git remote -v: No remote -> work on current branch. Has remote -> use EnterWorktree, never commit directly to main.

  • All PRs target YOUR_DEV_BRANCH, not main. Branch from YOUR_DEV_BRANCH.
  • Two gates before auto-merge: Senior Reviewer + Docs. Watchdog merges after both pass.
  • Mega PR (YOUR_DEV_BRANCH -> main) for your CTO's manual review. Never auto-merge to main.
  • YOUR_DEV_BRANCH = working prod. If a dependency is in YOUR_DEV_BRANCH, it's available -- don't block on it.
  • If YOUR_DEV_BRANCH doesn't exist: git checkout -b YOUR_DEV_BRANCH main && git push -u origin YOUR_DEV_BRANCH
  • Never stash another agent's changes while agents are active. SQLite not tracked in git.

Core Rules

  1. Read project CLAUDE.md first
  2. Design before code: Clarify -> Plan with approval -> Code
  3. TDD: Failing tests (min 3 fail + 1 pass) -> Implement -> All pass
  4. Task tracking: Notion = engineering (rules/notion-tracking.md). Command Center = business. No task files in customer repos.
  5. Simplicity first: Minimal changes. Root causes. Senior dev standards.
  6. Self-improvement: After corrections -> update Command Center tasks/lessons.md

Workflow

  • Plans: Interactive -> plan mode for 3+ steps. Autonomous loops -> Notion comment, never plan mode UI.
  • Priority: High+Low -> High+Med -> Med+Low -> High+High -> Med+Med -> Med+High -> Low+Low -> Low+Med -> Low+High
  • Quality gates: Tests pass. "What was NOT tested" on every PR. Screenshots/blogs = Docs agent's job.

Magic Keywords

Keyword What it does
"prep sprint" Query board -> propose tasks totaling >= 20 SP (floor, not ceiling) -> you approve -> check Move to Current Sprint checkbox. MUST exclude any task tagged Requires: Me. Priority order: (1) full AFK-able epics, (2) prelim tasks inside epics that can ship without you, (3) High, (4) Medium, (5) Low. Within each tier, prefer Low Risk first (you can ship unverified). Use My Current Sprint view (YOUR_CURRENT_SPRINT_VIEW_ID) to check current state. See rules/loop-afk-vs-live.md.
"prep session" Surfaces tasks tagged Requires: Me, grouped by session subtag (Session: Creds / Taste / Money / CTO / Device). Output is a batched to-do list for your next in-person work block, NOT a sprint. See rules/loop-afk-vs-live.md.
"launch swarm" Requires Current Sprint curated. Fires local /loop commands via the loop skill for Sprint Worker (30m), Watchdog (10m), Reviewer (20m), Planner (15m), Docs (20m). Each loop needs its own terminal. Cloud triggers were tried and abandoned (2026-04-05) -- they 500'd on manual run and the 1h min interval was too coarse. Local loops require laptop awake but have full access to Playwright, AWS creds, test env SSH, Payload secret. See rules/loop-modes.md.
"prep for deploy" Run tests -> open PR targeting YOUR_DEV_BRANCH -> report.
"prep for review" Opens draft mega PR with structured review table. You comment fix #N: reason or revert #N on the PR. See rules/loop-review.md.
"batch fix" Reads your mega PR comments, reverts revert items, ships fix PRs for fix items, updates mega PR. See rules/loop-review.md.
"ship clean" Ships what's ready NOW -- reverts all fix + revert items, marks mega PR ready. Held items go to next sprint.
"prep mega pr" (Legacy) Sync YOUR_DEV_BRANCH <- main -> run tests -> verify all sub-PR gates -> open mega PR per loop-back-testing.md -> notify your CTO via Slack.

Read the full file on GitHub · 61 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. 9d ago First seen · 61 lines · 1,237 tokens per session scan A 5f1ae20852d6

Subscribe to this mod's changes

launch-swarm CLAUDE.md is an instructions file published in the GitHub repository harshmoney123/launch-swarm (7 stars, last pushed 4mo ago), licensed MIT. It adds 1,237 tokens to every session, about $0.0062 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.

Related

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.

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens