llm-wiki-loop: Skill for Claude Code

.claude/skills/wiki-ingest/SKILL.md

wiki-ingest is a skill for Claude Code from helicerat/llm-wiki-loop. It costs 55 tokens per session (556 once invoked), scanned A, original, MIT.

A workflow for reading new source files and adding their information to a local wiki. It records whether a source is new or changed and leaves the original file untouched.

In plain words
What is it for?
Use it when adding documents from a raw folder to an existing wiki, updating pages with new sources, and marking inferred or uncertain information.
Why use it?
It prevents duplicate wiki pages and avoids repeatedly processing files that have not changed, while keeping track of where claims came from.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is helicerat/llm-wiki-loop's own configuration. It tells Claude Code how to work on llm-wiki-loop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki-loop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to helicerat/llm-wiki-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/helicerat/llm-wiki-loop/main/.claude/skills/wiki-ingest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/helicerat/llm-wiki-loop

Made for: Claude Code.

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 wiki-ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-ingest.svg)](https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-ingest)
Your own site
<a href="https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-ingest"><img src="https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-ingest.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 556 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 $0.00055 $0.00556
Opus 5 $0.00028 $0.00278
Sonnet 5 $0.00011 $0.00111
Haiku 4.5 $0.00006 $0.00056

Measured 8d ago against content hash 8558cf9ee9ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

.claude/skills/wiki-ingest/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-ingest

A source enters. Pages change. The source does not.

Before reading

Check .manifest.json for the source's SHA-256. Four possible answers: new, modified, unchanged, missing. Only new and modified are processed.

Hash the content — never trust modification time. Sync, checkout, and touch all lie about mtime and produce phantom reprocessing that costs real tokens and rewrites pages for nothing.

Read

Read the source from raw/. Do not edit it. Do not move it. Do not "clean it up" first — the copy in raw/ is the thing you will need in six months when a claim built on it is challenged.

Write

Update existing pages before creating new ones. The point of a compiled wiki is that a second source on a subject makes the existing page better, not that it makes a second page.

As you write, mark provenance inline:

  • no marker — the source states this explicitly
  • ^[inferred] — you generalised, filled a gap, or connected two sources
  • ^[ambiguous] — the source is vague, or it conflicts with something already in the wiki

Roll the fractions up into page frontmatter. Above 40% inferred with no sources listed is unsourced synthesis; on a hub page the threshold is 20%.

When a source contradicts an existing page, do not resolve it silently. Write both, dated, and leave the contradiction visible. Silent reconciliation is how a wiki loses the information that it was ever uncertain.

Claims

If the source supports a falsifiable claim about your domain, create the claim page from templates/claim.md. It starts at status: candidate, n: 0.

Ingesting a source never increments n. Reading three articles that all say the same thing is one belief with three citations, not a replicated finding. n moves only through wiki-measure, only from an outcome. Keeping these separate is the point of the whole structure — everything else here is bookkeeping.

Finish

Update wiki/index.md. Append one line to wiki/log.md:

## [YYYY-MM-DD] ingest | source title

Read the full file on GitHub · 61 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. 8d ago First seen · 61 lines · 55 tokens per session scan A 8558cf9ee9ba

Subscribe to this mod's changes

wiki-ingest is a skill published in the GitHub repository helicerat/llm-wiki-loop (6 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 556 once invoked, about $0.0003 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

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-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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