flow-maintenance

flow-maintenance is a skill for Claude Code, Codex from pwdev-solucoes/pwdev-claude-marketplace. It costs 47 tokens per session (502 once invoked), scanned A, original, Apache-2.0.

A project-history tool for inventorying, archiving, and summarizing PWDEV Flow work. It identifies stale or completed artifacts, archives only approved completed directories, and can create changelogs from verified history.

In plain words
What is it for?
Use it to find old artifacts, preview safe archive moves, archive approved completed work, or summarize verified project history as a changelog.
Why use it?
It helps keep Flow workspaces understandable over time without deleting important configuration, active work, memory, or audit records.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the pwdev-flow plugin — 17 skills, 1 command shipped together

Good fit Use it to find old artifacts, preview safe archive moves, archive approved completed work, or summarize verified project history as a changelog.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance
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-maintenance
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.

agentmods badge for flow-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance)
Your own site
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance/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 flow-maintenance

Your own site · 80×15
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 502 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00502
Opus 5 $0.00023 $0.00251
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 6d ago against content hash a7bd51e933a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

flow-maintenance 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.

plugins/pwdev-flow/skills/flow-maintenance/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maintain PWDEV Flow History

Read maintenance, artifacts, audit, and safety before proposing changes.

Route

  • inventory is read-only and classifies each candidate as active, complete, stale, or archivable.
  • archive moves only explicitly approved, verified-complete phase or quick-task directories.
  • changelog derives a preview from real Git commits and verified Flow execution summaries.

If the request is ambiguous, begin with inventory; it does not authorize archiving.

Inventory

  1. Read state, active product and phase contracts, verification verdicts, memory links, migration records, and audit references.
  2. List exact candidate paths, classification evidence, size, dependencies, and proposed archive destination.
  3. Preserve config, state, context, product contracts, memory, audit data, migration records, and the active phase.

Archive

  1. Produce the inventory and require explicit approval for the exact source paths and destinations.
  2. Resolve destinations below .planning/flow/archive/<date>/; refuse every collision instead of overwriting.
  3. Move only approved directories whose verification verdict is APPROVED and which are no longer active.
  4. Update authorized state references, then record archived through flow_audit.py when audit is enabled.
  5. Verify that every approved source moved, every destination exists, and no unapproved path changed.

Changelog

Read actual Git history and verified Flow summaries. Use an explicit version or Unreleased, preserve existing CHANGELOG.md content, exclude fabricated or reverted work, and present a preview before writing unless the user already authorized file generation.

Constraints

  • Never delete artifacts, use recursive cleanup, rewrite Git history, or archive incomplete work.
  • A stale artifact is a finding, not automatically an archive candidate.
  • Do not infer approval for archive targets from a general cleanup request.

Read the full file on GitHub · 45 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.

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. 6d ago First seen · 45 lines · 47 tokens per session scan A a7bd51e933a8

Subscribe to this mod's changes

flow-maintenance is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 47 tokens to every session and 502 once invoked, about $0.0002 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.

Related

Other skills, from other repositories