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

Authoring rules for an engineering-leadership plugin that provides AI agents for refining requirements, setting technical direction, and governing delivery.

Use it when adding or editing leadership agents, documenting their triggers and delegation relationships, and organizing project-specific knowledge and memory.

They keep agent definitions, descriptions, formatting, memory settings, and role colors consistent across the plugin.

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

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/CLAUDE.md

Clone the repo

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

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

Your own site

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

Per session 1,004 This file is loaded in full into every session.

When invoked 1,004 The same file — it is already loaded in full.

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	$0.01004	$0.01004
Opus 5.5	$0.00402	$0.00402
Sonnet 5.5	$0.00201	$0.00201
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash 84a6f42340f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-engineering-leaders CLAUDE.md 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.

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

engineering-leaders

A Claude Code plugin providing engineering leadership agents — the virtual leadership team that refines requirements, sets technical direction, and governs delivery.

Authoring Conventions

Markdown Body

Always add a blank line between a heading (or bold-text header like **Triggers:**) and the following list or paragraph. Omitting the blank line violates MD022/MD032 and can cause rendering issues.

Agents

One markdown file per agent in agents/
Follow the agent definition template: frontmatter (name, description, model, memory) + body (jurisdiction, delegation, key knowledge, memory protocol)
Descriptions must include trigger phrases AND delegation relationships
All agents use memory: project — they learn per-project
Agent names use kebab-case

Agent colors are assigned by role to ensure visual distinction in the Claude Code UI:

Agent	Color	Rationale
chief-architect	blue	Strategic authority, long-term thinking
product-owner	yellow	Planning and prioritization (sticky-note energy)
ux-strategist	magenta	Creative, user-empathy, experience focus
agile-coach	green	Process health, go/no-go signals
devops-lead	cyan	Infrastructure, operational tooling
engineering-manager	orange	Meta-observation, systemic feedback
qa-lead	red	Quality gates, risk signals
tech-lead	purple	Tactical orchestration, convention ownership

Skills

One directory per skill in skills/<skill-name>/
Must contain SKILL.md with YAML frontmatter
Skills are opinionated procedures with clear inputs, process steps, and outputs
Use $ARGUMENTS for parameterization
Use context: fork for skills that produce a lot of output (keeps main context clean)
Skills can bundle data files in subdirectories — reference them via Glob/Read relative to the skill directory

Agent vs Skill Decision

If it needs to learn and decide → agent
If it needs to execute a procedure → skill
Agents use skills; skills don't use agents
Agents reference skills with the / prefix (e.g., /write-runbook) in their markdown — Claude invokes the skill autonomously when the agent's instructions call for it

Read the full file on GitHub · 95 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 · 95 lines · 1,004 tokens per session scan A 84a6f42340f7

Subscribe to this mod's changes

claude-code-engineering-leaders CLAUDE.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 1,004 tokens to every session, about $0.0040 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.

Building agents

claude-code-engineering-leaders CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-engineering-leaders CLAUDE.mdcpliakas/claude-code-engineering-leaders	Instructions file	4	1mo ago	MIT	A	1,004	Claude Code
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