What is claude-code-engineering-leaders AGENTS.md?

Repository instructions for developing the `engineering-leaders` Claude Code plugin, a plugin with virtual engineering leadership roles and software-development skills.

Editing agents, skills, hooks, and tests in the plugin repository while following its naming, metadata, layout, and authoring conventions.

They give AI agents the project structure, writing rules, and testing guidance needed to change the plugin consistently.

How cpliakas/claude-code-engineering-leaders configures Claude Code an

Reuse

Borrowing it

Nothing to install: this file belongs to cpliakas/claude-code-engineering-leaders. 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/cpliakas/claude-code-engineering-leaders/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leaders

Made for: Claude Code, Codex, OpenCode.

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/instructions/cpliakas/claude-code-engineering-leaders/agents-md/github.svg)](https://agentmods.dev/instructions/cpliakas/claude-code-engineering-leaders/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cpliakas/claude-code-engineering-leaders/agents-md"><img src="https://agentmods.dev/badge/instructions/cpliakas/claude-code-engineering-leaders/agents-md/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/instructions/cpliakas/claude-code-engineering-leaders/agents-md"><img src="https://agentmods.dev/badge/instructions/cpliakas/claude-code-engineering-leaders/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 713 This file is loaded in full into every session.

When invoked 713 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.00713	$0.00713
Opus 5.5	$0.00285	$0.00285
Sonnet 5.5	$0.00143	$0.00143
Haiku 4.5	$0.00071	$0.00071

Measured 2mo ago against content hash 3cc4794b2d58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

claude-code-engineering-leaders AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf directory # NOT: rm -r directory

AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working in this repository.

Project Overview

engineering-leaders is a Claude Code plugin providing a virtual engineering leadership team. It ships eight leadership agents (Chief Architect, Product Owner, UX Strategist, Agile Coach, DevOps Lead, Engineering Manager, QA Lead, Tech Lead) and fifteen skills covering the full SDLC: requirement refinement, story/epic/ADR/runbook authoring, retrospectives, postmortems, and more.

The plugin is installed into other projects. Development work happens here; consumer projects install it from the marketplace or a local path.

Repository Layout

agents/     One .md file per agent (frontmatter + body)
skills/     One subdirectory per skill, each containing SKILL.md
hooks/      Plugin-level Claude Code hooks
tests/      Manual test scenarios (scenarios.md)

Authoring Conventions

Full conventions are documented in CLAUDE.md. Key rules for agents:

Agents (agents/<name>.md)

Frontmatter fields: name, description, model, color, memory: project
description must include trigger phrases and delegation relationships
Names use kebab-case; colors are fixed per role (see CLAUDE.md)
Body sections: Jurisdiction, Delegation, Key Knowledge, Memory Protocol

Skills (skills/<name>/SKILL.md)

Frontmatter: name, description, and optionally context: fork
Use $ARGUMENTS for parameterization
Use context: fork for skills that produce heavy output
Data files for a skill live in subdirectories of its skill directory

Agent vs. Skill

Needs to learn and decide over time → agent
Executes a fixed procedure → skill
Agents invoke skills with /skill-name; skills do not invoke agents

Onboarding model

/onboard — shared project context, writes to .claude/agent-memory/engineering-leaders/PROJECT.md
/onboard-<agent> — per-agent context on top of the shared layer

Testing

Tests are manual scenarios in tests/scenarios.md. To run them:

Read the full file on GitHub · 93 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 · 93 lines · 713 tokens per session scan C 3cc4794b2d58

Subscribe to this mod's changes

claude-code-engineering-leaders AGENTS.md is an instructions file published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 1mo ago), licensed MIT. It adds 713 tokens to every session, about $0.0029 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claude-code-engineering-leaders AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-engineering-leaders AGENTS.mdcpliakas/claude-code-engineering-leaders	Instructions file	4	1mo ago	MIT	C	713	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-code-engineering-leaders: Instructions file for Claude Code