reference

reference is a skill for Claude Code, Codex from panaversity/agentfactory-business-plugins. It costs 94 tokens per session (1,937 once invoked), scanned A, original, Apache-2.0.

A guide for writing employment or professional reference letters and confirming facts such as a person's job title and dates of employment.

In plain words
What is it for?
Use it to prepare factual or professional references, employment confirmations, and salary or employment-detail checks when the required consent and policy information are available.
Why use it?
It helps keep references truthful, protect private employee information, and ensure HR reviews sensitive letters before they are sent.

Skill for Claude CodeCodex

Part of the hr-operations plugin — 5 skills, 4 agents shipped together

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 skills/panaversity/agentfactory-business-plugins/reference
Any agent
npx skills add panaversity/agentfactory-business-plugins --skill reference
Clone the repo
git clone --depth 1 https://github.com/panaversity/agentfactory-business-plugins

Made for: Claude Code, Codex.

Or install hr-operations, the plugin that ships this one along with the rest of its 5 skills, 4 agents.

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 reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/reference.svg)](https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/reference)
Your own site
<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/reference"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,937 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 $0.00094 $0.01937
Opus 5 $0.00047 $0.00968
Sonnet 5 $0.00019 $0.00387
Haiku 4.5 $0.00009 $0.00194

Measured 4d ago against content hash b0612384b63e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

hr-operations/skills/reference/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UNIVERSAL RULES (apply to every reference task)

  • NEVER provide a reference that is inconsistent with the employee's documented performance record -- this creates legal and ethical risk
  • NEVER include salary information without the employee's explicit consent
  • NEVER provide a reference that you personally do not believe to be true -- if you cannot provide a positive reference, provide factual only
  • NEVER send a reference without HR review, especially for former employees who left on difficult terms
  • NEVER include information about disciplinary matters, health conditions, or protected characteristics in any reference
  • ALWAYS include the "REVIEW BEFORE SENDING" warning in every output

BEFORE IMPLEMENTATION

Source Check
Conversation Employee name, reference type requested (factual/professional/verification), recipient and purpose if known
hr.local.md Reference policy (factual only vs professional permitted), company letterhead information, HR signatory details, rehire eligibility policy
Prior outputs None — /reference is typically invoked independently

CLARIFICATION QUESTIONS

Required (ask if not provided):

  • Who is the reference for? (employee name)
  • What type of reference is needed? (factual / professional / employment verification)

Optional (ask if context suggests value):

  • Who is the recipient and what is the purpose? (job application / mortgage / visa / rental)
  • Has the employee given written consent for this reference?
  • Is there specific information the recipient has requested?

Read the full file on GitHub · 252 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 252 lines · 94 tokens per session scan A b0612384b63e

Subscribe to this mod's changes

reference is a skill published in the GitHub repository panaversity/agentfactory-business-plugins (28 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,937 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

internal-linking-optimizer

Use when improving internal link structure, anchor text, orphan pages, crawl depth, site architecture, or link equity flow. 内链优化/站内架构.

ViryaZheng/recomby-geo · 38 tokens

geo-review-html

Render an interactive, self-contained HTML companion for a GEO content brief (04-content-brief) or a publish-ready draft (05-production), so a NON-technical client reviewer (founder, organizer staff, the domain expert filling slots) can fill REQUIRED-FILL slots, leave section-level comments, and approve/return work in…

ViryaZheng/recomby-geo · 140 tokens

schedule

Create, list, remove or inspect this bot's scheduled work — recurring jobs ("every morning at 7 tell me X", "every weekday at 9 post the standup") and one-shot follow-ups ("check back in 20 minutes", "watch that deploy until it lands", "remind me on Friday"). Use whenever something must happen on a schedule…

xrgarcia/slashbin-ai-team · 92 tokens

kanban-codex-lane

Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.

S3YED/appie-kit · 42 tokens

coding-agents

Delegate coding tasks to external autonomous AI coding CLI agents — Claude Code, Codex, OpenCode, and Kanban+Codex lane patterns. Covers install, auth, one-shot tasks, interactive sessions, PR reviews, parallel worktrees, and reconciliation.

S3YED/appie-kit · 55 tokens

code-quality

Code quality and verification: codebase metrics, post-implementation cleanup, and pre-commit verification pipeline.

S3YED/appie-kit · 24 tokens