What is soloflow CLAUDE.md?

A CLAUDE.md file is a set of project instructions that tells coding agents how a repository is organized and which rules to follow. These instructions describe SoloFlow, a tool that coordinates product work through stages such as planning, implementation, and verification.

It is for guiding work on the SoloFlow repository, including project constraints, release and branch practices, and rules about hooks and agents.

It gives agents the project context and prevents them from using SoloFlow’s own workflow incorrectly while changing its code.

How kesteva/soloflow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kesteva/soloflow. 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/kesteva/soloflow/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kesteva/soloflow

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/kesteva/soloflow/claude-md/github.svg)](https://agentmods.dev/instructions/kesteva/soloflow/claude-md)

Your own site

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

Per session 1,058 This file is loaded in full into every session.

When invoked 1,058 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	$0.01058	$0.01058
Opus 5.5	$0.00423	$0.00423
Sonnet 5.5	$0.00212	$0.00212
Haiku 4.5	$0.00106	$0.00106

Measured 2mo ago against content hash f65c77fe6c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

soloflow 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 2mo 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 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

SoloFlow is a hooks-based Claude Code workflow orchestration system that automates the product development lifecycle: idea extraction → refinement → execution → verification → learning. Distributed as a Claude Code plugin (git repo + thin plugin wrapper) installable per-project or globally.

See docs/ARCHITECTURE.md for the phase workflow, hook system, agent model strategy, and verification hierarchy.

This repo does not dogfood SoloFlow on itself. SoloFlow is the product built here, not the workflow used to build it. Do not run /soloflow:* commands, create .soloflow/ state, spawn SoloFlow agents, or otherwise invoke the SoloFlow pipeline to make changes to this codebase. Work on SoloFlow the way you'd work on any other repo: read files, make edits, run tests, commit. If a request seems to imply "use SoloFlow to improve SoloFlow," stop and ask — it's almost certainly not what the user meant.

Constraints every agent must know

Subagents cannot spawn subagents. Orchestration runs in the main session (/soloflow:sprint, /soloflow:compound, etc.); executors, verifiers, reviewers, and all other agent definitions are leaf nodes only.

Parallel task loops share a per-task worktree. When /soloflow:sprint or /soloflow:mad-max runs multiple non-conflicting tasks concurrently (governed by limits.max_parallel_tasks), the orchestrator creates a short-lived git worktree per task at .soloflow/worktrees/TASK-NNN/ and injects WORKTREE_ROOT: <abs path> into every subagent prompt for that task. Subagents must honor the directive (see each agent's "Working directory" section). Merge-back + settle-task.js run sequentially from the main worktree.

Context-limit handoffs. hooks/statusline.js writes context metrics to a bridge file; hooks/context-monitor.js (PostToolUse) reads it and injects WARNING (≤35% remaining) / CRITICAL (≤25%) into the agent conversation.

Read the full file on GitHub · 44 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.

2mo ago First seen · 44 lines · 1,058 tokens per session scan A f65c77fe6c12

Subscribe to this mod's changes

soloflow CLAUDE.md is an instructions file published in the GitHub repository kesteva/soloflow (40 stars, last pushed 5mo ago), licensed MIT. It adds 1,058 tokens to every session, about $0.0042 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 2026-08-30.

soloflow CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
soloflow CLAUDE.mdkesteva/soloflow	Instructions file	40	5mo ago	MIT	A	1,058	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

soloflow: Instructions file for Claude Code