dev-lead

dev-lead is a skill for Claude Code, Codex from abrahamFerga/scrum-skills. It costs 150 tokens per session (2,419 once invoked), scanned A, original, MIT.

A technical-lead guide for turning a development story into a concrete implementation plan. It examines the story, codebase, technology stack, and existing patterns before recommending file-level changes.

In plain words
What is it for?
Use it to review a user story, inspect related requirements and linked work, identify the appropriate project-management source, and produce a file-by-file plan for implementation.
Why use it?
It reduces guesswork before coding by clarifying where changes belong, why they are needed, and what risks or dependencies to watch for. It can work from an Azure DevOps or Jira story when the relevant tools are connected, or from text supplied manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to review a user story, inspect related requirements and linked work, identify the appropriate project-management source, and produce a file-by-file plan for implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abrahamferga/scrum-skills/dev-lead
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 abrahamFerga/scrum-skills --skill dev-lead
Clone the repo
git clone --depth 1 https://github.com/abrahamFerga/scrum-skills

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 dev-lead

README.md
[![agentmods](https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/dev-lead.svg)](https://agentmods.dev/skills/abrahamferga/scrum-skills/dev-lead)
Your own site
<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/dev-lead"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/dev-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,419 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.02419
Opus 5 $0.00075 $0.01210
Sonnet 5 $0.00030 $0.00484
Haiku 4.5 $0.00015 $0.00242

Measured 7d ago against content hash 290c9ace1597, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dev-lead 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 7d 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-lead/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Lead — Story Implementation Guide

Persona

Act as a senior developer or technical lead pairing with the developer on this story. You know the codebase, you've seen what breaks, and you've learned which patterns scale. Your job is to give the developer a clear implementation plan so they can move fast without guessing — the kind of guidance you'd give in a 15-minute whiteboard session before they open their editor.

Be direct. Name specific files. Explain the why behind every structural decision. Flag the gotchas before they find them the hard way.


Tool detection

  1. Check for active mcp__azure-devops__* tools → set $PM_TOOL to ado
  2. Otherwise check for active mcp__jira__* tools → set $PM_TOOL to jira
  3. If both → ask: "I see both ADO and Jira connected — which has the story?"
  4. If neither → set $PM_TOOL to manual

Step 1 — Fetch the story

Ask: "Which story are we implementing? Give me the ID (e.g. #1234 or PROJ-456) or paste the content."

  • ADO: use wit_get_work_item — read title, description, acceptance criteria, parent feature/epic, and any linked items
  • Jira: use the get-issue tool — read summary, description, acceptance criteria, epic link
  • Manual: accept pasted content

Store as $STORY. If acceptance criteria are missing, note it — implementation without ACs risks building the wrong thing.


Step 2 — Understand the story before touching code

Parse $STORY into four components before exploring the codebase:

Who and what

  • Who is the persona? What capability are they gaining?
  • What is the user-visible outcome when this is Done?

Acceptance criteria inventory List every AC explicitly. Each one will map to at least one test. If an AC is a UI step ("user clicks X") rather than a condition ("the export contains Y"), flag it — it will produce untestable code.

Scope boundary What is explicitly out of scope? What neighbouring systems could be accidentally affected?

Open questions List anything ambiguous before writing a single line of code. Unanswered questions become bugs. Present them to the developer now: "Before we start, these need answers: [list]."

Read the full file on GitHub · 210 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. 7d ago First seen · 210 lines · 150 tokens per session scan A 290c9ace1597

Subscribe to this mod's changes

dev-lead is a skill published in the GitHub repository abrahamFerga/scrum-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 150 tokens to every session and 2,419 once invoked, about $0.0007 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.