mflow

Guidance for using mflow, a live file-synchronization layer for coordinating people or AI agents working in separate worktrees. A worktree is an additional working copy of a Git repository.

In plain words
What is it for?
Use it when checking sync status, coordinating edits, managing locks, or pausing synchronization before commits, rebases, resets, or branch changes. It also covers setup approval and handling missing or stopped mflow.
Why use it?
It helps prevent conflicting edits and unsafe Git operations while making clear that synchronization is not version control, secret storage, or a replacement for code review.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/obed0101/mflow/mflow
Any agent
npx skills add Obed0101/mflow --skill mflow
Clone the repo
git clone --depth 1 https://github.com/Obed0101/mflow

Made for: Claude Code, Codex.

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.01306
Opus 5 $0.00039 $0.00653
Sonnet 5 $0.00015 $0.00261
Haiku 4.5 $0.00008 $0.00131

Measured 2d ago against content hash 036d16981683, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mflow 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 2d 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.

skills/mflow/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mflow Skill

mflow keeps local worktrees synchronized while humans or AI agents edit. Treat it as a live sync layer, not as git, not as a secret manager, and not as a substitute for review.

Non-negotiables

  • Never print, commit, log, or paste room secrets/API keys.
  • Do not install, start, or configure mflow/MCP in a user's environment unless the human/project owner explicitly approves it.
  • Before creating or changing harness hook files, call mflow hook-status and ask for human approval if the active harness is still manual.
  • Before commit/rebase/reset/branch surgery: pause mflow, inspect status and git diff, do the git operation, then resume.
  • Use queued locks for hot files before parallel edits: shared config, migrations, schemas, auth, package manifests, generated public docs.
  • If mflow is absent or stopped, do not assume peers are synced. Say so and continue with normal git safety.
  • Hosted accounts are optional. The core OSS workflow is room + strong shared secret.

Before installing

If mflow is not already installed or configured, explain this to the human first:

  • The CLI starts a local daemon that watches project files.
  • The MCP server gives the agent status, peers, pause/resume, and lock controls.
  • Room secrets must be generated by the human and never printed.
  • This skill can be copied into agent runtimes that support skills.

Ask whether they want CLI only, CLI + MCP, or CLI + MCP + skill installation.

Quick start

npm i -g mflow-cli
export MFLOW_SECRET="$(openssl rand -hex 32)"
mflow start --room <repo>/<branch-or-task> --secret "$MFLOW_SECRET"
mflow status --watch

Join another worktree with the same room and secret:

mflow start --room <repo>/<branch-or-task> --secret "$MFLOW_SECRET"

Safe agent workflow

  1. Check sync state:
mflow hook-status
mflow status
mflow locks

If the active harness reports a missing hook, say that optional coordinated edit hooks are available, ask whether the human wants that installed now, and only then run mflow install-hooks --harness <supported-harness>. If the harness is Codex, explain that mflow install-hooks --harness codex creates an experimental scaffold that still needs local verification before relying on it.

Read the full file on GitHub · 176 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. 2d ago First seen · 176 lines · 77 tokens per session scan A 036d16981683

Subscribe to this mod's changes

mflow is a skill published in the GitHub repository Obed0101/mflow (2 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,306 once invoked, about $0.0004 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 skills, from other repositories

joining-a-room

Use when the user wants to join, open, create or leave a Pairdown room, when they mention a room id or a Pairdown link, when they ask what rooms exist, or when they ask why an agent is not showing up in a room. Covers attaching a session to a room, how being summoned works, and the two things that usually go wrong.

rohanrichards/pairdown · 78 tokens

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

semantic-compression

Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…

can1357/oh-my-pi · 77 tokens

durable-session-state

Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…

ZaxbyHub/opencode-swarm · 70 tokens

install-skill

Install a pasted SKILL.md (or one fetched from a URL or file path) into the user-skill directory, reviewing risk and connector requirements.

Open-Curiosity/gini-agent · 34 tokens