A command that splits a task among parallel Codex command-line sessions, choosing how they may access the project.

Use it to fan out a task across Codex sessions in default, writable, read-only, or explicitly unrestricted modes.

It avoids handling every part of a large task in one session and can run independent pieces at the same time. Its modes control whether sessions can write files or only inspect them.

wiki-ingest — Skill for Claude Code and Codex by AIwork4me

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/AIwork4me/open-llm-wiki

agentmods

npx agentmods add skills/aiwork4me/open-llm-wiki/wiki-ingest

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aiwork4me/open-llm-wiki/wiki-ingest/github.svg)](https://agentmods.dev/skills/aiwork4me/open-llm-wiki/wiki-ingest)

Your own site

<a href="https://agentmods.dev/skills/aiwork4me/open-llm-wiki/wiki-ingest"><img src="https://agentmods.dev/badge/skills/aiwork4me/open-llm-wiki/wiki-ingest/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aiwork4me/open-llm-wiki/wiki-ingest"><img src="https://agentmods.dev/badge/skills/aiwork4me/open-llm-wiki/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,459 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.

Model	Per session	Once invoked
Fable 5.1	$0.00116	$0.02459
Opus 5	$0.00058	$0.01229
Sonnet 5	$0.00023	$0.00492
Haiku 4.5	$0.00012	$0.00246

Measured 10d ago against content hash 28210203453a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wiki-ingest 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 10d 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/wiki-ingest/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Ingest

Ingest one source document into an open-llm-wiki vault. Optimize for traceability, safe file changes, and independent verification rather than speed.

Runtime Tools

Prefer deterministic runtime scripts when they are available in either the repo or the vault:

<repo>/scripts/wiki_lint.py
<vault>/.open-llm-wiki/scripts/wiki_lint.py
<repo>/scripts/wiki_grow.py
<vault>/.open-llm-wiki/scripts/wiki_grow.py
<repo>/scripts/wiki_claims.py
<vault>/.open-llm-wiki/scripts/wiki_claims.py
<repo>/scripts/wiki_normalize_metrics.py
<vault>/.open-llm-wiki/scripts/wiki_normalize_metrics.py
<repo>/scripts/wiki_semantic_qa.py
<vault>/.open-llm-wiki/scripts/wiki_semantic_qa.py
<repo>/scripts/wiki_science_review.py
<vault>/.open-llm-wiki/scripts/wiki_science_review.py
<repo>/scripts/wiki_discover_sources.py
<vault>/.open-llm-wiki/scripts/wiki_discover_sources.py
<repo>/scripts/wiki_queue.py
<vault>/.open-llm-wiki/scripts/wiki_queue.py
<repo>/scripts/wiki_contradictions.py
<vault>/.open-llm-wiki/scripts/wiki_contradictions.py
<repo>/scripts/wiki_concept_revision.py
<vault>/.open-llm-wiki/scripts/wiki_concept_revision.py
<repo>/scripts/pdf_corpus_to_markdown.py
<vault>/.open-llm-wiki/scripts/pdf_corpus_to_markdown.py
<repo>/scripts/pdf_to_markdown.py
<vault>/.open-llm-wiki/scripts/pdf_to_markdown.py
<repo>/scripts/wiki_search.py
<vault>/.open-llm-wiki/scripts/wiki_search.py

Run lint before and after ingest:

uv run python scripts/wiki_lint.py "<vault>" --fail-on p1

Safety Boundary

Run only after the user explicitly asks to ingest a source.
Process one source at a time. Do not batch ingest unless the user asks for a serial queue and confirms the order.
Work only inside the resolved wiki vault. Never write outside raw/, drafts/, sources/, concepts/, qa-reports/, claims/, _state/, templates/, index.md, or log.md.
Treat raw/ as immutable evidence. Do not edit, rename, or delete source files. Write parsed text to a new file.
Use local parsing by default. Use cloud OCR only when the user has configured credentials and accepts that document content leaves the local machine.
Before publishing or changing concept pages, summarize the planned file changes. If the user requested a fully automated ingest, continue and record all changes in log.md.
Never silently overwrite a stable source page, QA report, or contradiction report. Create a new draft or ask the user how to handle the conflict.

Read the full file on GitHub · 267 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.

10d ago First seen · 267 lines · 116 tokens per session scan A 28210203453a

Subscribe to this mod's changes

wiki-ingest is a skill published in the GitHub repository AIwork4me/open-llm-wiki (2 stars, last pushed 4mo ago), licensed MIT. It adds 116 tokens to every session and 2,459 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 2026-08-31.

Documents LLM Research ai-agent karpathy knowledge-base obsidian pkm

kb-index

Update Knowledge Base indexes. Smart mode detects changes and updates only what's needed. Full rebuild available with --full flag. Use after adding/moving documents or when indexes feel stale.

ernestolee13/para-knowledge-base · 38 tokens

second-reader

Build and run a source-verified Markdown knowledge vault (opens as an Obsidian vault). Ingests books, PDFs, transcripts, and articles into atomic, cross-linked, cited notes, then gates every note and every answer behind an independent verification pass that re-reads the source cold and loops until a round finds…

mplind/second-reader · 191 tokens

wiki-ingest