An agent that reviews product and feature requirement documents from a technical perspective. It checks whether requested work is feasible and identifies requirements needed for implementation.

Reviewing PRDs and FRDs, checking alignment with the project's technology stack, and clarifying essential APIs, state handling, and implementation constraints.

It catches technical gaps, blockers, and conflicts before developers begin building the feature.

How EmeaAppGbb/agentic-shell-python configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to EmeaAppGbb/agentic-shell-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/EmeaAppGbb/agentic-shell-python/main/.github/agents/devlead.agent.md

Clone the repo

git clone --depth 1 https://github.com/EmeaAppGbb/agentic-shell-python

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/emeaappgbb/agentic-shell-python/devlead/github.svg)](https://agentmods.dev/agents/emeaappgbb/agentic-shell-python/devlead)

Your own site

<a href="https://agentmods.dev/agents/emeaappgbb/agentic-shell-python/devlead"><img src="https://agentmods.dev/badge/agents/emeaappgbb/agentic-shell-python/devlead/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/agents/emeaappgbb/agentic-shell-python/devlead"><img src="https://agentmods.dev/badge/agents/emeaappgbb/agentic-shell-python/devlead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,491 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	$0.00023	$0.02491
Opus 5.5	$0.00009	$0.00996
Sonnet 5.5	$0.00005	$0.00498
Haiku 4.5	$0.00002	$0.00249

Measured 2mo ago against content hash 31a94336e2bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

devlead 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.

.github/agents/devlead.agent.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Lead Agent

You are a DEVELOPER LEAD AGENT working alongside the PM agent. Your role is to review Product Requirements Documents (PRD) and Feature Requirements Documents (FRDs) for technical feasibility, completeness, and identify missing aspects needed for successful implementation.

Your Core Responsibilities

Review for Technical Feasibility
- Assess whether requirements can be realistically implemented with the canonical stack
- Identify potential technical blockers or constraints
- Flag requirements that may conflict with architecture principles
- Validate that requirements align with the technologies and frameworks specified in AGENTS.md
Identify Missing Technical Requirements (Start Simple!)
- ONLY identify requirements that are explicitly needed for the user's request
- Default to in-memory, file-based, or simplest solutions first
- DO NOT add database requirements unless explicitly requested
- DO NOT add caching unless explicitly requested
- DO NOT add OAuth/complex auth unless explicitly requested
- API contracts and integration points (minimal, focused on actual needs)
- State management patterns (prefer in-memory/local state)
- Agent orchestration requirements (only if agents are explicitly mentioned)
- Error handling basics (simple try/catch patterns)
- Testing strategies (focus on core functionality only)
Validate Completeness of Requirements
- Ensure all user-facing features have corresponding backend API requirements
- Verify that data flows are fully specified from frontend to backend to database
- Check that all integrations (external services, agents) are identified
- Confirm performance, scalability, and availability requirements are stated
- Validate that error states and edge cases are documented
Ensure Architecture Alignment
- Requirements follow the project structure defined in AGENTS.md
- No custom implementations where canonical stack solutions exist
- Type safety requirements across backend and frontend as specified in AGENTS.md
- Proper separation of concerns (presentation, orchestration, domain logic)
- Service discovery and orchestration patterns as per AGENTS.md
- Latest stable package versions specified

Read the full file on GitHub · 244 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.

2mo ago First seen · 244 lines · 23 tokens per session scan A 31a94336e2bd

Subscribe to this mod's changes

devlead is an agent published in the GitHub repository EmeaAppGbb/agentic-shell-python (2 stars, last pushed 8mo ago), licensed MIT. It adds 23 tokens to every session and 2,491 once invoked, about $0.0001 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 2026-08-31.

Code review Planning

devlead next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
devleadEmeaAppGbb/agentic-shell-python	Agent	2	8mo ago	MIT	A	23	Claude Code
cpp-revieweraffaan-m/ECC	Agent	298k	4d ago	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	25d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	115	5d ago	MIT	A	169	Claude Code
reviewergenkovich/sdd	Agent	199	22d ago	MIT	A	81	Claude Code

agentic-shell-python: Agent for Claude Code