run-workflow

run-workflow is a command for Claude Code from khanh-vu/claude-force. It costs 6 tokens per session (520 once invoked), scanned A, original, MIT.

A command that runs a predefined sequence of coding agents for a particular type of work. The available sequences cover full-stack features, frontend work, backend APIs, and documentation.

In plain words
What is it for?
Use it to coordinate architecture, implementation, testing, deployment, API development, or documentation work. Choose a workflow based on whether the task involves the whole application, only the frontend, only the backend, or written documentation.
Why use it?
It removes the need to choose and coordinate each specialist separately for a multi-step task. Each agent's output is validated before the next agent runs.

Command for Claude Code

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 commands/khanh-vu/claude-force/run-workflow
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

Made for: Claude Code.

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 run-workflow

README.md
[![agentmods](https://agentmods.dev/badge/commands/khanh-vu/claude-force/run-workflow.svg)](https://agentmods.dev/commands/khanh-vu/claude-force/run-workflow)
Your own site
<a href="https://agentmods.dev/commands/khanh-vu/claude-force/run-workflow"><img src="https://agentmods.dev/badge/commands/khanh-vu/claude-force/run-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 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 $0.00006 $0.00520
Opus 5 $0.00003 $0.00260
Sonnet 5 $0.00001 $0.00104
Haiku 4.5 $0.00001 $0.00052

Measured 4d ago against content hash 6eea360cfd4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-workflow 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.

.claude/commands/run-workflow.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Workflow Command

Execute a predefined workflow with multiple agents in sequence.

Available Workflows

1. full-stack-feature

Complete feature from architecture to deployment.

Agents (8):

  1. frontend-architect
  2. database-architect
  3. backend-architect
  4. python-expert
  5. ui-components-expert
  6. frontend-developer
  7. qc-automation-expert
  8. deployment-integration-expert

Use for: New features requiring both frontend and backend work.

2. frontend-only

Frontend-focused development workflow.

Agents (4):

  1. frontend-architect
  2. ui-components-expert
  3. frontend-developer
  4. qc-automation-expert

Use for: UI features, component libraries, client-side functionality.

3. backend-only

Backend API development workflow.

Agents (4):

  1. backend-architect
  2. database-architect
  3. python-expert
  4. qc-automation-expert

Use for: API endpoints, services, data processing.

4. documentation

Documentation generation workflow.

Agents (2):

  1. document-writer-expert
  2. api-documenter

Use for: Technical docs, API documentation, user guides.

Workflow Execution

For each agent in the workflow:

  1. Execute agent with full governance
  2. Validate output
  3. Confirm success before proceeding
  4. If failure, stop workflow and report
  5. Update progress in context file
  6. Proceed to next agent

Progress Tracking

The command will:

  • Show current agent and progress (e.g., "Agent 3 of 8")
  • Pause between agents for review (optional)
  • Report completion status
  • Provide summary of all artifacts

Example

/run-workflow full-stack-feature

This will execute all 8 agents in the full-stack workflow.

Options

/run-workflow full-stack-feature --no-pause

Run without pausing between agents.

/run-workflow frontend-only --start-from ui-components-expert

Resume workflow from specific agent.

Notes

  • Requires .claude/task.md to be properly filled out
  • Each agent must pass validation before next one starts
  • Can interrupt and resume later from same point
  • Progress logged in context_session_1.md

Read the full file on GitHub · 102 lines

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 · 102 lines · 6 tokens per session scan A 6eea360cfd4b

Subscribe to this mod's changes

run-workflow is a command published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It adds 6 tokens to every session and 520 once invoked, about $0.0000 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.