flow-execute

flow-execute is a skill for Claude Code, Codex from pwdev-solucoes/pwdev-claude-marketplace. It costs 45 tokens per session (489 once invoked), scanned A, original, Apache-2.0.

A workflow tool for carrying out approved software plans one small task at a time, with tests and verification at each stage.

In plain words
What is it for?
Use it to implement planned changes, write failing tests first for behavior changes, run focused and broader checks, inspect the final diff, and report blockers.
Why use it?
It keeps implementation within the agreed scope and catches problems before moving to the next task. It also records evidence and stops when the plan or dependencies are no longer valid.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: $skill-name invocation.

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

Good fit Use it to implement planned changes, write failing tests first for behavior changes, run focused and broader checks, inspect the final diff, and report blockers.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-execute.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-execute)
Your own site
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-execute"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/flow-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 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 $0.00045 $0.00489
Opus 5 $0.00023 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 4d ago against content hash b458b8b251b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

flow-execute 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 4d 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-execute/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute approved tasks

Read execution, planning, collaboration, memory, artifacts, and safety.

Entry gate

Require an approved plan, satisfied dependencies, and identifiable verification commands. Stop if the plan is stale, contradicts the specification, or overlaps unrelated user changes unsafely.

Procedure

  1. Execute inline by default. Select one ready task; do not mix tasks or waves in one implementation unit.
  2. Read the full task, linked specification clauses, required context, applicable instructions, relevant memory, and current Git status.
  3. Confirm allowed files and state the task contract before editing.
  4. For behavior changes, write the focused failing test first and observe the expected failure.
  5. Implement only the approved actions with the smallest sufficient change.
  6. Run focused verification, then the relevant broader suite.
  7. Inspect the complete diff for scope, correctness, safety, and prohibited behavior.
  8. Write the execution summary specified by execution and update state only from fresh evidence.
  9. Continue to the next ready task only when the current result is COMPLETE or an accepted CAVEATS.
  10. After all tasks, set REVIEW_REQUIRED and recommend $flow-simplify or $flow-review.

Blockers and corrections

On NEEDS_ADVICE, stop edits, persist the structured question, and request one decision. For fix plans, follow the same lifecycle and enforce the maximum correction cycles. Never silently redesign scope.

Collaboration and Git

Use collaborating workers only when the user explicitly requests delegation or parallel agent work. Never assign overlapping writers and independently verify returned claims.

Do not commit, push, create a branch, clean files, or rewrite history unless the user explicitly authorizes that exact action. Leave the diff reviewable.

Read the full file on GitHub · 40 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. 4d ago First seen · 40 lines · 45 tokens per session scan A b458b8b251b6

Subscribe to this mod's changes

flow-execute is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 489 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.