kb-ingest-bulk

kb-ingest-bulk is a skill for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 112 tokens per session (1,335 once invoked), scanned A, original, MIT.

A bulk-ingestion workflow for loading many sources into a knowledge base. It uses a map-reduce process: separate agents extract information, then other agents combine it into library files.

In plain words
What is it for?
Use it to ingest files or source lists in parallel, route findings to library topics, merge them into files, retry failed items, and finish by rebuilding the index and recording the run.
Why use it?
It organises large source collections into existing or new topics without requiring one agent to read and write everything in a single pass.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdlc-knowledge-base plugin — 16 skills, 4 agents shipped together

Good fit Use it to ingest files or source lists in parallel, route findings to library topics, merge them into files, retry failed items, and finish by rebuilding the index and recording the run.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SteveGJones/ai-first-sdlc-practices
Claude Code
/plugin install sdlc-knowledge-base

Made for: Claude Code.

Or install sdlc-knowledge-base, the plugin that ships this one along with the rest of its 16 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 kb-ingest-bulk

README.md
[![agentmods](https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-ingest-bulk/github.svg)](https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-ingest-bulk)
Your own site
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-ingest-bulk"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-ingest-bulk/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-ingest-bulk

Your own site · 80×15
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-ingest-bulk"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-ingest-bulk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,335 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 $0.00112 $0.01335
Opus 5 $0.00056 $0.00668
Sonnet 5 $0.00022 $0.00267
Haiku 4.5 $0.00011 $0.00134

Measured 11d ago against content hash b261f69b2e05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kb-ingest-bulk 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 11d 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/sdlc-knowledge-base/skills/kb-ingest-bulk/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bulk Ingestion (map-reduce)

Load a large source set into the knowledge base in parallel. Four phases: map (parallel extract) → route (Python) → reduce (parallel synthesis, one writer per file) → finalize (one rebuild + one log entry).

Arguments

Argument Description
<glob|dir|file-list> Sources to ingest
--library <path> Target library, bypassing CLAUDE.md resolution (default: CLAUDE.md-resolved). For isolated testing / multi-library — see #209
--parallel <N> Concurrency for map + reduce rounds (default 16, max 64)
--extractor-model <id> Map model (default claude-haiku-4-5)
--size-threshold <tokens> Per-file reduce size guard (default 200000)
--retry-failed Re-queue failed sources/targets from a prior run
--clean Remove library/.extracts/ after a successful run

Preflight

  1. Resolve library_path: if --library given, use it; else read CLAUDE.md ## Knowledge Base section. Derive shelf_index_path = <library>/_shelf-index.md, log_path = <library>/log.md, extracts_dir = <library>/.extracts.
  2. Verify knowledge-extractor and agent-knowledge-updater agents are available.
  3. Clamp --parallel to [1, 64].

Module bootstrap

Use this CLAUDE_PLUGIN_ROOT importlib loader block to import the sdlc_knowledge_base_scripts.kb_ingest_bulk helpers. It is self-contained — no other file needs to be opened.

python3 -c "
import sys, os, importlib.util, json
PLUGIN_ROOT = os.environ.get('CLAUDE_PLUGIN_ROOT', '')
SCRIPTS = os.path.join(PLUGIN_ROOT, 'scripts')
INIT = os.path.join(SCRIPTS, '__init__.py')
if os.path.isfile(INIT) and 'sdlc_knowledge_base_scripts' not in sys.modules:
    spec = importlib.util.spec_from_file_location(
        'sdlc_knowledge_base_scripts', INIT, submodule_search_locations=[SCRIPTS])
    if spec and spec.loader:
        mod = importlib.util.module_from_spec(spec)
        sys.modules['sdlc_knowledge_base_scripts'] = mod
        spec.loader.exec_module(mod)
from sdlc_knowledge_base_scripts.kb_ingest_bulk import (
    discover_sources, build_bulk_manifest, load_manifest, save_manifest,
    retry_failed, persist_extract, slug_for_source, mark_source_extracted,
    mark_source_failed, route_extracts, format_extract_prompt,
    format_reduce_prompt, ReduceDispatchRequest, mark_target_reduced,
    mark_target_failed, summarize_run, write_log_entry, ExtractDispatchRequest
)
"

Read the full file on GitHub · 102 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. 11d ago First seen · 102 lines · 112 tokens per session scan A b261f69b2e05

Subscribe to this mod's changes

kb-ingest-bulk is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,335 once invoked, about $0.0006 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

embeddings

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.

ruvnet/ruflo · 62 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

browserwing-admin

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

MemTensor/MemOS · 47 tokens