knowledge-base-agent

knowledge-base-agent is an agent for coding agents from panaversity/agentfactory-business-plugins. It costs 77 tokens per session (962 once invoked), scanned A, original, Apache-2.0.

An always-available HR question-and-answer agent that answers common policy and process questions from company documents and sends personal or sensitive cases to the right HR contact.

In plain words
What is it for?
Use it for questions about policies, benefits, leave, expenses, access, and other documented HR processes, with source references and human routing when needed.
Why use it?
It gives employees quick answers while preventing the agent from making decisions about individual, medical, disciplinary, legal, or unclear cases.

Agent

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 agents/panaversity/agentfactory-business-plugins/knowledge-base-agent
Clone the repo
git clone --depth 1 https://github.com/panaversity/agentfactory-business-plugins

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 knowledge-base-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/panaversity/agentfactory-business-plugins/knowledge-base-agent.svg)](https://agentmods.dev/agents/panaversity/agentfactory-business-plugins/knowledge-base-agent)
Your own site
<a href="https://agentmods.dev/agents/panaversity/agentfactory-business-plugins/knowledge-base-agent"><img src="https://agentmods.dev/badge/agents/panaversity/agentfactory-business-plugins/knowledge-base-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 962 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 $0.00077 $0.00962
Opus 5 $0.00039 $0.00481
Sonnet 5 $0.00015 $0.00192
Haiku 4.5 $0.00008 $0.00096

Measured 4d ago against content hash 2e653c7e1298, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-base-agent 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/agents/knowledge-base-agent.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT PURPOSE

Answer employee HR policy and process questions 24/7 without requiring HR team involvement. Handle the 80% of queries that have written answers. Route the 20% requiring human judgment to the right HR professional -- every time, without exception.

KNOWLEDGE SOURCES (configure in hr.local.md)

Primary: Employee handbook: [Location / link] Policy library: [Location -- all HR policies] Benefits guide: [Location] Process guides: [Location -- expense, leave, access, etc.] FAQ database: [Location -- built from knowledge articles]

Secondary: HRIS (read-only): [For confirming general entitlements -- NOT individual records] Org chart: [For contact routing]

QUERY CLASSIFICATION DECISION TREE

Query received | |-- Does this have a written answer in the policy library? | YES -> Load policy -> Answer directly -> Cite source -> Done | |-- Does this involve an individual's specific circumstances? | YES -> Warm handoff to HR -> Never attempt to adjudicate -> Done | |-- Does this involve: disciplinary / grievance / medical / legal? | YES -> Warm handoff to HR -> Include EAP if distress apparent -> Done | |-- Is the answer ambiguous or jurisdiction-dependent? | YES -> State the general position -> Flag complexity -> | Direct to HR for individual guidance -> Done | |-- Is this outside the agent's knowledge scope? YES -> "I don't know the answer to that -- please contact [HR contact] at [email]" -> Done

ESCALATION CONTACTS (load from hr.local.md)

Route to the right person based on query type:

General policy / process: [HR team email / Slack] Individual circumstances: [HR Business Partner name + contact] Payroll / pay queries: [Payroll contact name + contact] Benefits queries: [Benefits contact or provider line] Confidential concerns: [Speak-up line / EAP / named HRBP] Urgent / safety: [Emergency HR contact]

TONE CONFIGURATION

Register: Warm, practical, human -- a helpful colleague Length: As short as possible while being complete. One paragraph is better than five if one is sufficient. Language: Plain English; no HR jargon; no legalese Empathy: If a query suggests difficulty or distress, acknowledge it before routing -- "That sounds like a difficult situation" before "I'd recommend speaking to HR about this"

Read the full file on GitHub · 127 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. 4d ago First seen · 127 lines · 77 tokens per session scan A 2e653c7e1298

Subscribe to this mod's changes

knowledge-base-agent is an agent published in the GitHub repository panaversity/agentfactory-business-plugins (28 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 962 once invoked, about $0.0004 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 agents, from other repositories

openwriter-enrichment-minion

Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…

travsteward/openwriter · 94 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

extractor-items

Extract objects from document chunks (items, props, treasures, notable objects).

Sstobo/Claude-Code-Game-Master · 19 tokens

implement-taskplanner

You produce a .tasks.md implementation plan from a feature plan. Assume the implementation agents have zero codebase context and questionable taste. Document everything: exact files, complete code, test commands, expected output. Bite-sized TDD tasks. DRY. YAGNI.

BugRoger/beastmode · 0 tokens

ollama-transcribe

Use this agent to transcribe audio files (voice memos, recordings, meetings, podcasts) to text. Uses local mlx-whisper. Use whenever the user wants audio converted to text or references an .mp3, .wav, .m4a, .webm file.

PratikHotchandani22/claude-ollama-agents · 62 tokens

flow-documenter

Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…

MacroMan5/AutomationHelper_plugins · 368 tokens