A project-state tool for setting up, inspecting, resuming, or migrating PWDEV Flow workspaces. It checks repository instructions, project files, workflow state, and legacy configuration without opening secret files.

Use it to initialize Flow in a repository, resume paused work, inspect the next valid action, or plan migration from a legacy PWDEV Code workspace.

It helps you understand where a PWDEV Flow project currently stands and prevents existing workflow state from being overwritten accidentally.

flow-init — Skill for Claude Code and Codex by pwdev-solucoes

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.

Any agent

npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill flow-init

Clone the repo

git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code, Codex.

Or install pwdev-flow, the plugin that ships this one along with the rest of its 17 skills, 1 command.

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/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-init/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-init)

Your own site

<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-init"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-init/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/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-init"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 719 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00051	$0.00719
Opus 5	$0.00026	$0.00360
Sonnet 5	$0.00010	$0.00144
Haiku 4.5	$0.00005	$0.00072

Measured 5d ago against content hash 13812d6e30f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flow-init 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 5d 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.

plugins/pwdev-flow/skills/flow-init/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize PWDEV Flow

Read workflow, artifacts, migration, and safety before changing project state.

Procedure

Inspect the repository without reading secrets:
- locate AGENTS.md and read applicable instructions;
- treat CLAUDE.md as optional compatibility context when present;
- inspect manifests, source layout, tests, and recent Git history;
- never open .env, credentials, tokens, private keys, or certificates.
Check for .planning/flow/config.json, .planning/flow/state.md, and the legacy .planning/config.json.
Route the request as inspect, initialize, or migrate:
- if Flow state exists, do not overwrite it; summarize the active workflow, last gate, artifacts, and next valid action;
- if legacy config exists and Flow config does not, report a migration candidate instead of initializing over it;
- use migrate only when the user asks to adopt the legacy workspace.
For migrate:
- resolve migrate_legacy.py from this installed plugin and run plan with the active repository root and --runtime <your adapter>;
- present mappings, excluded field names, and conflicts without exposing excluded values;
- stop for explicit approval before apply;
- after approval, run apply, create missing Flow state/directories without overwriting existing paths, and inventory legacy artifacts in .planning/flow/migration.md;
- do not copy or move legacy artifacts without a second approval for exact paths;
- record migrated through the audit helper only when the migrated config enables audit.
If state does not exist and the user requested fresh initialization:
- classify the repository as greenfield or brownfield from existing source and history;
- create .planning/flow/quick/ and .planning/flow/reports/;
- create configuration and state using the exact schemas in artifacts;
- set the artifact language from the user's current language unless explicitly configured otherwise;
- record runtime as the adapter you are running as, claude or codex; it is metadata about who initialized the workspace and never makes the artifacts unreadable from the other runtime;
- set auto_commit to false.
Report created, migrated, or discovered paths and recommend one next action.

Read the full file on GitHub · 49 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 193 B

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.

5d ago First seen · 49 lines · 51 tokens per session scan A 13812d6e30f0

Subscribe to this mod's changes

flow-init is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 719 once invoked, about $0.0003 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 2026-09-03.

Project management

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens