What is workflow-mcp?

A set of operations for managing workflow plans and audit records in a project’s .workflow folder. MCP is a tool connection that lets software exchange structured information with an agent.

Checking workflow status, creating or updating plans and audits, writing their artifacts, recording handoffs, and normalizing findings.

It keeps plan and audit state consistent when work is created, resumed, updated, or completed, without treating tool access as permission to start work.

workflow-mcp — Skill for Claude Code by wiolett-industries/marketplace

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 wiolett-industries/marketplace --skill workflow-mcp

Clone the repo

git clone --depth 1 https://github.com/wiolett-industries/marketplace

Made for: Claude Code.

Or install workflow, the plugin that ships this one along with the rest of its 9 skills, 17 agents, 1 hook.

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/wiolett-industries/marketplace/workflow-mcp/github.svg)](https://agentmods.dev/skills/wiolett-industries/marketplace/workflow-mcp)

Your own site

<a href="https://agentmods.dev/skills/wiolett-industries/marketplace/workflow-mcp"><img src="https://agentmods.dev/badge/skills/wiolett-industries/marketplace/workflow-mcp/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/wiolett-industries/marketplace/workflow-mcp"><img src="https://agentmods.dev/badge/skills/wiolett-industries/marketplace/workflow-mcp.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 700 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	$0.00700
Opus 5.5	$0.00020	$0.00280
Sonnet 5.5	$0.00010	$0.00140
Haiku 4.5	$0.00005	$0.00070

Measured 2mo ago against content hash 96f366c282a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow-mcp 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 2mo 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/workflow/skills/workflow-mcp/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow MCP

Use the matching MCP tool for deterministic .workflow/ state and artifact operations whenever it is available. This is the normal path, not a preference. MCP does not generate substantive content, launch agents, merge worktrees, run verification, or replace judgment.

.workflow/ is the default artifact root. When workflow_status reports a configured root from mcp-config.yml, treat the reported path as authoritative; do not assume or manually recreate the default directory.

Tool Surface

workflow_status
workflow_plan_create, workflow_plan_update, workflow_plan_complete, workflow_plan_artifact_write
workflow_plan_commitment_propose, workflow_plan_commitment_confirm
workflow_audit_create, workflow_audit_update, workflow_audit_complete, workflow_audit_artifact_write
workflow_handoff_write
workflow_findings_normalize

Loading this skill never authorizes a new plan/audit. The active primary workflow and action boundary decide whether artifacts may exist.

Core Contract

Pass an absolute workspace_root when cwd may be a parent or sibling workspace.
Call workflow_status at start/resume, after compaction, or when active state is uncertain; do not call it before every phase merely for reassurance.
New authorized work uses workflow_plan_create or workflow_audit_create. Existing unfinished work uses the matching update tool. Do not reopen completed runs without an explicit request.
Use artifact tools only for allowed run-relative paths. Pass exactly one of content or json.
Normalize structured findings before storing them.
Finish realized runs with workflow_plan_complete or workflow_audit_complete; phase-only updates do not clear the root active pointer.

Commitment reflection is platform-neutral state and same-model judgment. Use the propose/confirm tools for material plans before execution and after material scope divergence. A Codex Stop hook may enforce missing state, but skills and MCP remain complete without it; Claude Code and other clients must never be instructed to find or wait for that hook.

Read the full file on GitHub · 51 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.

references/operations.md 3.4 KB

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.

2mo ago First seen · 51 lines · 51 tokens per session scan A 96f366c282a3

Subscribe to this mod's changes

workflow-mcp is a skill published in the GitHub repository wiolett-industries/marketplace (10 stars, last pushed 15d ago), licensed MIT. It adds 51 tokens to every session and 700 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Project management

workflow-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
workflow-mcpwiolett-industries/marketplace	Skill	10	15d ago	MIT	A	51	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code