What is devflow-mcp CLAUDE.md?

Project instructions for DevFlow, a system that organizes AI-assisted development into stages such as planning, approval, implementation, review, and completion. Its server controls which actions are allowed at each stage.

Use them when working in the devflow-mcp project or any workflow that requires creating or selecting a flow, following allowed actions, and moving through controlled development stages.

They make the work process explicit and prevent development tools from being used before a session and flow are initialized. They also ensure that approval stages wait for a user’s decision.

How KlausFreiberufler/devflow-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to KlausFreiberufler/devflow-mcp. 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/KlausFreiberufler/devflow-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/KlausFreiberufler/devflow-mcp

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/klausfreiberufler/devflow-mcp/claude-md.svg)](https://agentmods.dev/instructions/klausfreiberufler/devflow-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/klausfreiberufler/devflow-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/klausfreiberufler/devflow-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,357 This file is loaded in full into every session.

When invoked 1,357 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	$0.01357	$0.01357
Opus 5	$0.00678	$0.00678
Sonnet 5	$0.00271	$0.00271
Haiku 4.5	$0.00136	$0.00136

Measured 6d ago against content hash fc90eeed1864, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

devflow-mcp 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 6d 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 · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevFlow - Strukturierte KI-Entwicklung

Projekt: DevFlow Project

Dieses Projekt nutzt DevFlow fuer strukturierte, nachvollziehbare KI-Entwicklung. Alle Regeln werden technisch vom MCP-Server erzwungen.

Arbeitsstart

BEVOR du mit der Arbeit beginnst:

flow_list() → Finde einen freien Flow
devflow_init({ flowId: "<id>" }) → Starte deine Session ODER
flow_create({ summary: "..." }) → Erstelle einen neuen Flow

Ohne devflow_init sind alle Tools blockiert.

Prozess

Der Server gibt dir bei jedem Schritt Anweisungen:

allowedActions → welche Tools du nutzen darfst
nextStep → was du als naechstes tun sollst

Folge den Anweisungen aus den Tool-Responses. Erlaubte Aktionen haengen vom Flow-State ab und werden vom Server erzwungen.

Flow-States

idea → planning → approval → ready → in_progress → review → done

Review-States (approval, review) sind Wartezustaende. Der User muss in der DevFlow-UI genehmigen bevor es weitergeht.

Regeln (Strictness-Level)

Flow-Pflicht: ⚖️ Balanced

Erstelle einen Flow bevor du arbeitest.

Planungs-Pflicht: ⚖️ Balanced

Erstelle einen Plan, warte aber nicht zwingend auf Approval.

Task-Tracking: ⚖️ Balanced

Erstelle Tasks und update ihren Status waehrend der Arbeit.

Git-Disziplin: ⚖️ Balanced

Halte Branch-Naming und Commit-Format ein.

Review-Pflicht: ⚖️ Balanced

Mache Self-Review (Diff pruefen, Findings fixen).

Docs-Update: 🏖️ Chill

Pruefe relevante Docs und aktualisiere sie bei Bedarf.

Knowledge-Pflicht (MCP-First)

Die DevFlow-Wissensdatenbank (ADRs / Patterns / Runbooks / Lessons Learned) wird ueber MCP-Tools gepflegt, NICHT ueber Backend-LLM-Aufrufe. Du bist die Intelligenz.

Regeln:

Nach jedem flow_update, der einen Flow auf done setzt, enthaelt die Response suggestedNextTool. Du MUSST diesen Hinweis befolgen und knowledge_harvest({ flowId }) aufrufen.
knowledge_harvest liefert den Flow, bestehende ADRs und Related-Drafts. Entscheide basierend darauf:
- Wenn das Thema schon durch einen ADR abgedeckt ist: skip.
- Wenn schon ein Draft fuer diesen Flow existiert: skip.
- Sonst: Entscheide, ob ADR / Pattern / Runbook / Lessons-Learned passt, und rufe knowledge_draft_create mit sinnvollem Titel + Body.

Read the full file on GitHub · 165 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.

6d ago First seen · 165 lines · 1,357 tokens per session scan A fc90eeed1864

Subscribe to this mod's changes

devflow-mcp CLAUDE.md is an instructions file published in the GitHub repository KlausFreiberufler/devflow-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 1,357 tokens to every session, about $0.0068 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.

Planning

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 · 5,182 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

devflow-mcp: Instructions file for Claude Code