build-knowledge-base

build-knowledge-base is a skill for Claude Code, Codex from doordash-oss/agentic-orchestrator. It costs 9 tokens per session (1,916 once invoked), scanned A, original, Apache-2.0.

A documentation skill that builds a structured knowledge base for a code repository. It organizes descriptions of the codebase into linked Markdown files instead of one large document.

In plain words
What is it for?
Use it to document a repository's structure, components, and relationships in a browsable directory of focused files.
Why use it?
It gives coding agents a map of the repository so they can find relevant system information progressively. It records what exists and how components interact without changing the code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it to document a repository's structure, components, and relationships in a browsable directory of focused files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doordash-oss/agentic-orchestrator/build-knowledge-base
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.

Any agent
npx skills add doordash-oss/agentic-orchestrator --skill build-knowledge-base
Clone the repo
git clone --depth 1 https://github.com/doordash-oss/agentic-orchestrator

Made for: Claude Code, Codex.

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 build-knowledge-base

README.md
[![agentmods](https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/build-knowledge-base.svg)](https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/build-knowledge-base)
Your own site
<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/build-knowledge-base"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/build-knowledge-base.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,916 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 105
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00009 $0.01916
Opus 5 $0.00005 $0.00958
Sonnet 5 $0.00002 $0.00383
Haiku 4.5 $0.00001 $0.00192

Measured 8d ago against content hash 3bec2ff8f291, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

build-knowledge-base 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 8d 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.

skills/build-knowledge-base/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Knowledge Base Graph

You are building a knowledge base (KB) graph for a code repository. The KB is a structured directory of focused documents — NOT a single monolithic file.

Output Files

Artifact Path Requirement Purpose
index.md {phase_dir}/index.md required top-level knowledge-base graph index markdown

CRITICAL: YOUR ONLY JOB IS TO DOCUMENT THE CODEBASE

  • DO NOT edit or modify any code files — you are a documenter, not an implementer
  • DO NOT suggest improvements or changes
  • DO NOT critique the implementation
  • ONLY describe what exists, where it exists, how it works, and how components interact
  • You are creating a technical map/documentation of the existing system

YOUR JOB

Produce a knowledge base graph: a directory structure with:

  1. A top-level index.md (~100-200 lines) that serves as the entry map
  2. Category subdirectories (you decide which categories fit the repo)
  3. Per-category index.md files summarizing that category
  4. Focused leaf files for specific topics

The goal is progressive disclosure: the index tells an agent what exists and where to find it. Agents read the index first, then drill into specific files only when they need deeper detail.

Output Structure

Write all files under the KB Root Directory specified in the prompt.

<KB Root Directory>/
├── index.md                    # THE ENTRY POINT — concise map
├── <category-1>/
│   ├── index.md                # category overview
│   └── <topic>.md              # focused deep-dives
├── <category-2>/
│   ├── index.md
│   └── <topic>.md
└── ...

Top-level index.md

This is the MOST IMPORTANT file. Keep it concise (~100-200 lines). It should contain:

  • One-paragraph project overview
  • Directory structure summary (top-level only)
  • Build/test/run commands (the most commonly needed info)
  • A category map: for each category dir, a one-line description and link
  • Key architectural decisions or patterns (brief bullets, link to details)

Read the full file on GitHub · 177 lines

Files

What ships with it

2 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. 8d ago First seen · 177 lines · 9 tokens per session scan A 3bec2ff8f291

Subscribe to this mod's changes

build-knowledge-base is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (102 stars, last pushed 3d ago), licensed Apache-2.0. It adds 9 tokens to every session and 1,916 once invoked, about $0.0000 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens