dev-workflow

dev-workflow is a skill for Claude Code, Codex from addxai/enterprise-harness-engineering. It costs 109 tokens per session (5,650 once invoked), scanned A, original, Apache-2.0.

A guided process for taking a software requirement from a user story through design documents, implementation, testing, and release. It requires confirmation before moving between its nine stages.

In plain words
What is it for?
Use it when starting or resuming a feature, requirement, or project and you need guidance on the current stage and the next action.
Why use it?
It keeps development work organized and makes sure requirements, monitoring plans, and test coverage are addressed before implementation.

Skill for Claude CodeCodex

Part of the enterprise-harness-engineering plugin — 25 skills shipped together

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/addxai/enterprise-harness-engineering/dev-workflow
Any agent
npx skills add addxai/enterprise-harness-engineering --skill dev-workflow
Clone the repo
git clone --depth 1 https://github.com/addxai/enterprise-harness-engineering

Made for: Claude Code, Codex.

Or install enterprise-harness-engineering, the plugin that ships this one along with the rest of its 25 skills.

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 dev-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/addxai/enterprise-harness-engineering/dev-workflow.svg)](https://agentmods.dev/skills/addxai/enterprise-harness-engineering/dev-workflow)
Your own site
<a href="https://agentmods.dev/skills/addxai/enterprise-harness-engineering/dev-workflow"><img src="https://agentmods.dev/badge/skills/addxai/enterprise-harness-engineering/dev-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,650 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 $0.00109 $0.05650
Opus 5 $0.00055 $0.02825
Sonnet 5 $0.00022 $0.01130
Haiku 4.5 $0.00011 $0.00565

Measured 4d ago against content hash db045e72eaf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-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.

skills/dev-workflow/SKILL.md · 618 lines

How it starts

The opening of the file, as written. The whole thing — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Workflow

Description

Standard R&D process orchestrator — guides the full development lifecycle from User Story to CD, with human confirmation required before proceeding to each step.

Collaboration with other skills: This skill is responsible for "what step are we on, what's next, and which skill to invoke"; architect handles "how to write the actual documents."

Every run must walk through the entire 9-step checklist — whether it is a new requirement, a new project, or a project already in progress — to ensure no critical step is missed (especially observability plans and test coverage).


Rules

  1. Mandatory full checklist: Every run must go from Step 1 to Step 9; no step may be skipped, even if its status is "Completed"
  2. Human confirmation at each step: After displaying the status of each step, wait for human confirmation ([y/N]) before proceeding to the next
  3. Observability is not optional: Step 5 (observability plan) is a required step and must not be skipped with "not needed for now"
  4. Documentation before code: Before Step 6 (TDD implementation), all documentation deliverables from Steps 1-5 must exist and be confirmed
  5. First-run initialization: When the project has no CLAUDE.md or no workspace skill, automatically run project initialization
  6. All User Stories must have E2E coverage: In Step 4's test plan, every User Story must have a corresponding L3 E2E test case

Examples

Bad — Skipping undiscovered missing steps

User: "Code is all done, MR is merged, help me set up CD"
AI: Directly discusses CD configuration...

Problem: Skipped the observability plan (Step 5), test plan check (Step 4), etc., jumping directly to the step the user mentioned.

Good — Enforced full checklist

User: "Code is all done, MR is merged, help me set up CD"
AI:
── Step 1 — User Story ──────────────
Status: Completed
Deliverable: docs/product/user-stories/postcard.md

Do you want to update this step? [y/N (default: skip)]

...(Steps 2-4 display status similarly)...

── Step 5 — Observability Plan ──────────────
Status: Missing
Deliverable: docs/architecture/postcard/observability.md — does not exist

Do you want to update this step? [y/N (default: skip)]

Read the full file on GitHub · 618 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 · 618 lines · 109 tokens per session scan A db045e72eaf3

Subscribe to this mod's changes

dev-workflow is a skill published in the GitHub repository addxai/enterprise-harness-engineering (44 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 109 tokens to every session and 5,650 once invoked, about $0.0005 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 2026-08-30.