projectflow-execute

projectflow-execute is a skill for Claude Code, Codex from wjmiracle/projectflow-dag-mcp. It costs 58 tokens per session (235 once invoked), scanned A, original, MIT.

A set of instructions for executing projects described as ProjectFlow graphs. A graph is a list of tasks connected by dependencies, showing which work must happen before other work.

In plain words
What is it for?
Loading a project, checking its status, claiming tasks, executing them in dependency order, and marking tasks done, failed, blocked, skipped, or reset.
Why use it?
It keeps task order and progress in the ProjectFlow service, including work that continues across sessions.

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/wjmiracle/projectflow-dag-mcp/projectflow-execute
Any agent
npx skills add wjmiracle/projectflow-dag-mcp --skill projectflow-execute
Clone the repo
git clone --depth 1 https://github.com/wjmiracle/projectflow-dag-mcp

Made for: Claude Code, Codex.

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 projectflow-execute

README.md
[![agentmods](https://agentmods.dev/badge/skills/wjmiracle/projectflow-dag-mcp/projectflow-execute.svg)](https://agentmods.dev/skills/wjmiracle/projectflow-dag-mcp/projectflow-execute)
Your own site
<a href="https://agentmods.dev/skills/wjmiracle/projectflow-dag-mcp/projectflow-execute"><img src="https://agentmods.dev/badge/skills/wjmiracle/projectflow-dag-mcp/projectflow-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 235 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 5.1 $0.00058 $0.00235
Opus 5 $0.00029 $0.00118
Sonnet 5 $0.00012 $0.00047
Haiku 4.5 $0.00006 $0.00023

Measured 4d ago against content hash befea07cbeb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

projectflow-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.

adapters/codex/projectflow-execute/SKILL.md · 18 lines

What it actually says

Execute ProjectFlow projects

Use the MCP server as the source of truth. Keep this adapter independent of any particular model.

  1. Call projectflow/get_execution_protocol before the first execution in a task and follow its returned protocol.
  2. Load the absolute graph path with load_project, then inspect status.
  3. Use claim_task for work. Use next_task only for a read-only preview.
  4. Perform the claimed task in the returned workspace and verify real artifacts.
  5. Call done_task only with a summary, output paths, and verification evidence.
  6. Use the dedicated fail, block, skip, and reset tools; never bypass MCP by editing the graph JSON.

If the MCP server is unavailable, stop and report the connection problem. Do not silently fall back to unvalidated direct JSON manipulation.

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 · 18 lines · 58 tokens per session scan A befea07cbeb0

Subscribe to this mod's changes

projectflow-execute is a skill published in the GitHub repository wjmiracle/projectflow-dag-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 235 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 2026-08-31.