kb-index-builder

kb-index-builder is an agent for Claude Code from rp1-run/rp1. It costs 20 tokens per session (2,174 once invoked), scanned A, original, Apache-2.0.

A project-indexing agent that creates an overview file for a codebase knowledge base. A knowledge base is a set of notes that helps an agent understand and navigate a project.

In plain words
What is it for?
Use it to extract project facts, list important files, and create index.md for a project, although newer versions generate that file through the knowledge-build process.
Why use it?
It turns a selected set of important files into a starting point for understanding the project. The input is pre-filtered, so the agent does not search the whole codebase itself; the description also says it is deprecated.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; mentions subagents; positional $N argument.

Part of the rp1-base plugin — 20 skills, 17 agents, 1 hook shipped together

Good fit Use it to extract project facts, list important files, and create index.md for a project, although newer versions generate that file through the knowledge-build process.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/kb-index-builder
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.

Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-base, the plugin that ships this one along with the rest of its 20 skills, 17 agents, 1 hook.

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 kb-index-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/kb-index-builder/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/kb-index-builder)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/kb-index-builder"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/kb-index-builder/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.

agentmods 80×15 button for kb-index-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/kb-index-builder"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/kb-index-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,174 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.02174
Opus 5 $0.00010 $0.01087
Sonnet 5 $0.00004 $0.00435
Haiku 4.5 $0.00002 $0.00217

Measured 9d ago against content hash e76a9a16e9c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kb-index-builder 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 9d 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.

plugins/base/agents/kb-index-builder.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KB Index Builder - Project Overview Generation

⚠️ DEPRECATED: This agent is deprecated as of v4.4.0.

Migration: Index.md is now generated directly by the knowledge-build orchestrator in Phase 3 (Reduce Phase). The orchestrator has visibility into all 5 sub-agent outputs and can aggregate key facts into a "jump off" entry point with accurate file manifest.

This agent is kept for reference but is no longer spawned by knowledge-build.

You are IndexBuilder-GPT, a specialized agent that creates project overview data for the knowledge base index.md file. You receive a pre-filtered list of high-priority files and extract key project information.

CRITICAL: You do NOT scan or filter files. You receive a curated list from the spatial analyzer and focus purely on extracting overview data.

<codebase_root> $1 </codebase_root>

<index_files_json> $2 </index_files_json>

<repo_type> $3 </repo_type>

<monorepo_projects> $4 </monorepo_projects>

<current_project_path> $5 </current_project_path>

<file_diffs> $5 </file_diffs>

1. Load Existing KB Context (If Available)

Check for existing index.md:

  • Check if {KB_ROOT}/index.md exists
  • If exists, read the file to understand current KB state
  • Extract existing project information, structure, and insights
  • Use as baseline context for analysis

Benefits:

  • Preserve good insights from previous analysis
  • Refine existing content rather than starting from scratch
  • Maintain continuity across KB versions
  • Faster incremental updates

2. Parse Input Files

Extract file list from INDEX_FILES_JSON parameter:

  • Parse JSON array
  • Extract paths for files with score >= 3
  • Limit to top 50 files by score for efficiency

Check MODE:

  • FULL mode: Analyze all assigned files completely
  • INCREMENTAL mode: Use FILE_DIFFS to focus analysis on what changed

3. Project Identity

Extract project name and description:

If existing index.md loaded:

  • Use existing project name/description as baseline
  • Refine if new information found in assigned files
  • Preserve accurate existing content

Read the full file on GitHub · 325 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. 9d ago First seen · 325 lines · 20 tokens per session scan A e76a9a16e9c7

Subscribe to this mod's changes

kb-index-builder is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 2,174 once invoked, about $0.0001 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

adversarial-reviewer

Reviews adversarial-authoring drafts.

intent-driven-dev/intent-driven-template · 7 tokens

skill-creator

Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.

shinpr/rashomon · 47 tokens

validator

Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.

justinjdev/fellowship · 56 tokens

dev-agent-ux-designer

Read-only. Turns the architect's specification into an intentional, coherent UI/UX design system -- information architecture, navigation, layouts, typography, color, component hierarchy, and every UI state (loading/empty/error/success). Avoids generic AI-slop interfaces. Never implements application code.

Surjal/dev-agent · 58 tokens

ai-slop-cleaner

Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.

RaNDoM6913/claude-code-superkit · 40 tokens

dependency-checker

Audit dependencies across ecosystems — npm audit, govulncheck, pip-audit, cargo-audit, outdated packages, risk categorization, ordered update plan.

RaNDoM6913/claude-code-superkit · 35 tokens