QUICK-REFERENCE

QUICK-REFERENCE is an agent for coding agents from Zeekeey-jpeg/LeRoy-HQ. It costs 0 tokens per session (2,238 once invoked), scanned A, original, MIT.

A quick reference for an organization of coding agents, showing who coordinates work, who can edit files, and who has read-only duties. It divides agents into five levels, from company leadership to support.

In plain words
What is it for?
Use it to check an agent's place in the hierarchy, editing permissions, reporting relationships, and technical area. It is a reference for routing tasks such as coding, design, data work, testing, and research.
Why use it?
It removes confusion about which agent should make changes and which should delegate, review, or monitor. This helps keep implementation work with the assigned specialists.

Agent

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 agents/zeekeey-jpeg/leroy-hq/quick-reference
Clone the repo
git clone --depth 1 https://github.com/Zeekeey-jpeg/LeRoy-HQ

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 QUICK-REFERENCE

README.md
[![agentmods](https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/quick-reference.svg)](https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/quick-reference)
Your own site
<a href="https://agentmods.dev/agents/zeekeey-jpeg/leroy-hq/quick-reference"><img src="https://agentmods.dev/badge/agents/zeekeey-jpeg/leroy-hq/quick-reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,238 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 $0.00000 $0.02238
Opus 5 $0.00000 $0.01119
Sonnet 5 $0.00000 $0.00448
Haiku 4.5 $0.00000 $0.00224

Measured 5d ago against content hash 722a1ad41bfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

QUICK-REFERENCE 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 5d 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.

core/agents/QUICK-REFERENCE.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Org Chart - Quick Reference

Version: 1.0


🎯 Core Principle

C-suite delegates, workers execute. Period.


5-Tier Hierarchy

Tier 1: C-Suite         → Coordination ONLY (NO Edit/Write)
Tier 2: VP Level        → Oversight ONLY (NO Edit/Write)
Tier 3: Management      → Limited Edit/Write (domain-specific)
Tier 4: Specialists     → Full Edit/Write (implementation)
Tier 5: Support         → Read-only (monitoring/research)

✅ Who Can Write Code?

Agent Can Edit/Write? Domain
builder ✅ YES Production code, tests, config
designer ✅ YES Design systems, UI components
forge ✅ YES Data operations, ETL, large-scale
professor ✅ YES Educational content, domain instruction
guardian ✅ YES QC audits, pre-commit validation
legal ✅ YES Contracts, legal docs
janitor ✅ YES Cleanup, maintenance
proposal-writer ✅ YES Sales proposals, presentations

❌ Who CANNOT Write Code?

Agent Tool Access Why
conductor (COO) Coordination only Delegates to builder/designer/forge
cto Coordination only Sets architecture, builder implements
vp-engineering Coordination only Reviews code, builder writes it
chief-of-staff Reports only Tracks timelines, doesn't implement
scout Read-only Observes patterns, doesn't modify
planner Read-only Tracks tasks, doesn't execute

🚨 Red Flags (Violations)

Critical Violations

  • ❌ C-suite uses Edit/Write tools
  • ❌ C-suite uses >15 tools per task
  • ❌ VP uses Edit/Write tools
  • ❌ Implementation work not delegated

How to Spot Violations

conductor (Design workflow) · 44 tool uses · 65.3k tokens
                                ^^^^^^^^^^
                        RED FLAG: Should have delegated!

What should happen instead:

conductor (Coordinate workflow) · 8 tool uses
  ├─ builder (Implement workflow) · 28 tool uses
  └─ guardian (Review workflow) · 12 tool uses

Read the full file on GitHub · 275 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. 5d ago First seen · 275 lines · 0 tokens per session scan A 722a1ad41bfb

Subscribe to this mod's changes

QUICK-REFERENCE is an agent published in the GitHub repository Zeekeey-jpeg/LeRoy-HQ (10 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,238 tokens. 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.