llm-wiki-capture-pipeline

llm-wiki-capture-pipeline is a skill for Claude Code, Codex from po4yka/llm-wiki-skills. It costs 71 tokens per session (1,069 once invoked), scanned A, original, MIT.

A design guide for collecting notes and source material into LLM-Wiki, a system for organizing information for language-model use. It covers capture from channels such as Telegram, email, Slack, PDFs, GitHub, and voice notes.

In plain words
What is it for?
Use it to design an inbox and raw-data layout, metadata rules, duplicate detection, privacy defaults, prompt-injection isolation, and handoffs to wiki-triage or wiki-ingest.
Why use it?
It reduces the need to decide where and how to file every item when capturing information. It also defines how captured material moves through review and ingestion while keeping privacy and untrusted content concerns explicit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design an inbox and raw-data layout, metadata rules, duplicate detection, privacy defaults, prompt-injection isolation, and handoffs to wiki-triage or wiki-ingest.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline
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 po4yka/llm-wiki-skills --skill llm-wiki-capture-pipeline
Clone the repo
git clone --depth 1 https://github.com/po4yka/llm-wiki-skills

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 llm-wiki-capture-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline/github.svg)](https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline)
Your own site
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline/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 llm-wiki-capture-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-capture-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,069 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 $0.00071 $0.01069
Opus 5 $0.00036 $0.00535
Sonnet 5 $0.00014 $0.00214
Haiku 4.5 $0.00007 $0.00107

Measured 12d ago against content hash c2453c6e2906, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

llm-wiki-capture-pipeline 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 12d 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/llm-wiki-capture-pipeline/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM-Wiki Capture Pipeline

Goal

Design the capture architecture that makes source capture fast, safe and reviewable across channels.

When to use

  • The user wants an inbox/raw topology, metadata contract or dedupe boundary designed for LLM-Wiki capture.
  • The user asks for a named-channel connector runbook (Telegram, email, Slack, Discord, Teams, browser clips, voice notes, PDFs, GitHub).
  • The user needs the triage handoff between capture and wiki-triage/wiki-ingest defined.
  • The user is setting privacy defaults or prompt-injection isolation rules for captured content.
  • The user is adding a new high-volume or low-confidence capture channel class to an existing vault/repo.

Core rule

Capture should require near-zero filing decisions. Put material into inbox/ or raw/ first; use wiki-triage and wiki-ingest later.

Inputs

  • Desired capture channel classes.
  • Existing vault/repo path.
  • Local-first/privacy requirements.
  • Target agent and automation environment.
  • Whether the output should stop at architecture or include named-channel connector rules.

Capture channel classes

Use classes here, not connector runbooks:

  • manual quick capture;
  • durable documents and sources;
  • media assets;
  • high-volume message streams;
  • meeting or transcript streams;
  • repo or ticket-system events.

Procedure

1. Choose capture boundary

Use one of:

Boundary Use when
inbox/ Material is messy, low-confidence or not yet worth ingestion.
raw/sources/ Source is trusted and should be preserved.
raw/assets/ Images, audio, screenshots, diagrams, media.
external event log High-volume streams that need dedup/retry before writing files.

2. Define the shared source envelope

Every captured item should include:

captured_at: YYYY-MM-DDTHH:mm:ssZ
capture_channel: web|voice|telegram|email|chat|manual|github|other
source_url: ""
source_author: ""
source_channel: ""
source_hash: ""
privacy: public|internal|sensitive
triage_status: new

Read the full file on GitHub · 158 lines

Files

What ships with it

1 file 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. 12d ago First seen · 158 lines · 71 tokens per session scan A c2453c6e2906

Subscribe to this mod's changes

llm-wiki-capture-pipeline is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 71 tokens to every session and 1,069 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

wiki-lint

Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…

tboome33/obsidian-mcp-router · 119 tokens

save

File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…

tboome33/obsidian-mcp-router · 112 tokens

wiki-export

Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…

tboome33/obsidian-mcp-router · 129 tokens

wiki-query

Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…

tboome33/obsidian-mcp-router · 129 tokens

wiki-fold

Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…

tboome33/obsidian-mcp-router · 125 tokens

wiki

Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…

tboome33/obsidian-mcp-router · 134 tokens