agentmods.dev

workflow

A command-based guide for tracking software work as issues, with required project steps and session records.

In plain words
What is it for?
Use it to view workflow status, start work, find matching issues, continue existing work, and follow the repository's tracking rules.
Why use it?
It helps prevent actionable tasks from being lost by connecting requests to issues, plans, progress, and verification.

Command for Claude Code

2 4mo ago A scan 6 tokens original MIT
View the source file JSMike/ai-workflow-starter
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/jsmike/ai-workflow-starter/workflow
Clone the repo
git clone --depth 1 https://github.com/JSMike/ai-workflow-starter

Made for: Claude Code.

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 1,846 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 $0.01846
Opus 5 $0.00003 $0.00923
Sonnet 5 $0.00001 $0.00369
Haiku 4.5 $0.00001 $0.00185

Measured 2d ago against content hash 79304e549e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/workflow.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Assistant

Helps ensure the issue tracking workflow is followed correctly. Canonical rules live in AGENTS.md; every actionable task in this repository must be tracked in .issues/.

Usage: /workflow [action]

Actions

(no action) - Overview

Display the complete workflow with current context. Show:

  1. Any in-progress issues from .issues/index.md
  2. The workflow steps
  3. Reminders about mandatory session-log entries

start

Begin work properly. Follow this checklist:

  1. Understand the request - What is the user asking for, and is it clear enough to plan?

  2. Clarify vague requests:

    • Restate the likely goal
    • Identify missing requirements, constraints, acceptance criteria, and non-goals
    • Ask targeted clarifying questions before creating an implementation-ready issue

  3. Check for existing issues:

    /issue match <description of the work>
    • If match found → Use /issue work <id> to continue
    • If no match → Use /issue create <title> to start new

  4. If continuing existing issue:

    • Read the issue.md for requirements
    • Read the plan.md for approach
    • Read the latest session-log.md entry for where we left off
    • Update status to in-progress if not already

  5. If creating new issue:

    • Use idea for exploration or vague requests
    • Use ready only when requirements and acceptance criteria are clear enough to implement
    • Plan file is at .issues/ISSUE-N/plan.md

  6. Confirm tracking:

    • Display: "Working on ISSUE-N: "
    • Display: "Remember to run /issue session ISSUE-N after completing work"

check

Verify the workflow is being followed. Check:

  1. Is there an active issue?

    • Scan .issues/*/issue.md for in-progress status
    • If none, warn: "No issue in progress - run /workflow start"

  2. Is the current work related to an issue?

    • Compare recent file changes to issue acceptance criteria
    • Warn if work appears untracked

Read the full file on GitHub · 247 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. 2d ago First seen · 247 lines · 6 tokens per session scan A 79304e549e88

Subscribe to this mod's changes

workflow is a command published in the GitHub repository JSMike/ai-workflow-starter (2 stars, last pushed 4mo ago), licensed MIT. It adds 6 tokens to every session and 1,846 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.

ProductivityProject management
Related

Other commands, from other repositories

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

project-recap

Generate a visual project recap for context switching.

nicobailon/visual-explainer · 12 tokens

speckit.taskstoissues

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

VisActor/VChart · 21 tokens

advisor

Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.

koolamusic/claudefiles · 41 tokens

guide

You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.

rjwalters/kicad-tools · 0 tokens

pm-review

Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.

wei63w/pm-manager · 19 tokens