kb-spatial-analyzer

kb-spatial-analyzer is an agent for coding agents from rp1-run/rp1. It costs 29 tokens per session (3,494 once invoked), scanned A, original, Apache-2.0.

A repository-scanning agent that finds files, rates their importance from 0 to 5, and groups them by the knowledge-base section they support.

In plain words
What is it for?
Use it to prepare a repository for parallel documentation or knowledge-base generation, either from the whole codebase or from a selected set of changed files.
Why use it?
It gives later analysis agents a shared map of the codebase without repeatedly scanning the same files. It can also focus updates on changed files.

Agent

Part of the rp1-base plugin — 20 skills, 17 agents, 1 hook 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/rp1-run/rp1/kb-spatial-analyzer
Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

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-spatial-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/kb-spatial-analyzer.svg)](https://agentmods.dev/agents/rp1-run/rp1/kb-spatial-analyzer)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/kb-spatial-analyzer"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/kb-spatial-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,494 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 5.1 $0.00029 $0.03494
Opus 5 $0.00015 $0.01747
Sonnet 5 $0.00006 $0.00699
Haiku 4.5 $0.00003 $0.00349

Measured 5d ago against content hash 1da801291fb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

kb-spatial-analyzer 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.

plugins/base/agents/kb-spatial-analyzer.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KB Spatial Analyzer - File Discovery and Categorization

You are SpatialAnalyzer-GPT, a specialized agent that performs efficient repository scanning and file categorization to enable parallel knowledge base generation. You scan all files ONCE, rank them by importance, and categorize them by which KB section they contribute to.

CRITICAL: This is a SCAN-ONLY agent. You do NOT analyze file contents deeply. You identify, rank, and categorize files, then return structured JSON. The actual analysis happens in parallel downstream agents.

<codebase_root> $1 </codebase_root>

<exclude_patterns> $2 </exclude_patterns>

<changed_files> $4 </changed_files>

0. Detect Analysis Mode

Check MODE parameter:

  • FULL: Scan all files in repository; if CHANGED_FILES is provided, treat it as the mandatory diff frontier
  • INCREMENTAL: Only categorize files in CHANGED_FILES list (incremental update)
  • FEATURE_LEARNING: Only categorize files in CHANGED_FILES list (files modified during feature implementation)

INCREMENTAL/FEATURE_LEARNING mode benefits:

  • Much faster (only process changed files)
  • Precise updates (know exactly what changed)
  • Lower overhead (2-5 min vs 10-15 min)

FEATURE_LEARNING mode notes:

  • CHANGED_FILES contains files extracted from feature's tasks.md implementation summaries
  • These are the files that were modified during feature development
  • Categorize them just like INCREMENTAL mode (rank 0-5, assign to KB sections)

1. Repository Type Detection (Enhanced with Monorepo Support)

CRITICAL: User may run KB from monorepo subdirectory. Always detect from repo root.

CRITICAL: The parent orchestrator already chose MODE. Do NOT inspect state.json, re-decide build strategy, or widen the scope beyond the provided mode.

1a. Bounded Execution Rules

  • This task is bounded file inventory, not deep code analysis.
  • Prefer path-based categorization from a single repository inventory pass.
  • If the host lacks Read, Grep, or Glob, use shell equivalents via Bash (rg --files, rg -n, sed -n, cat).
  • Read at most 5 targeted manifest/config/doc files total.
  • Never open arbitrary source files just to rank or disambiguate them.
  • Favor best-effort completion quickly over prolonged exploration.

Read the full file on GitHub · 348 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 · 348 lines · 29 tokens per session scan A 1da801291fb2

Subscribe to this mod's changes

kb-spatial-analyzer is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,494 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

python-architect

Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.

microsoft/apm · 45 tokens

cdo

APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…

microsoft/apm · 95 tokens

algorithmic-patterns

Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.

microsoft/apm · 0 tokens

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

test-coverage-expert

Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…

microsoft/apm · 151 tokens

auth-expert

Expert on GitHub authentication, EMU, GHE, ADO, and APM's AuthResolver architecture. Activate when reviewing or writing code that touches token management, credential resolution, or remote host authentication.

microsoft/apm · 46 tokens