llm-wiki-loop: Skill for Claude Code

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

wiki-check is a skill for Claude Code from helicerat/llm-wiki-loop. It costs 64 tokens per session (692 once invoked), scanned A, original, MIT.

A review skill that checks a finished draft against a project wiki before publication and reports factual conflicts or possible rule violations.

In plain words
What is it for?
Use it to review copy containing dates, figures, names, titles, quotations, or technical claims against the project’s documented sources.
Why use it?
It helps catch unsupported facts, incorrect quotations, and contradictions before a draft is released. It reports problems but does not rewrite the text.

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-check/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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-check.svg)](https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-check)
Your own site
<a href="https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-check"><img src="https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 692 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 $0.00064 $0.00692
Opus 5 $0.00032 $0.00346
Sonnet 5 $0.00013 $0.00138
Haiku 4.5 $0.00006 $0.00069

Measured 7d ago against content hash 7a7770c1417c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wiki-check 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 7d 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-check/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-check

The wiki points outward here. Every other operation asks whether the vault is healthy. This one asks whether the thing about to leave the vault contradicts what the vault has actually established.

Order

Run in order. A failure at step 0 cancels the rest — there is no point checking the rhythm of a draft that contains a number nobody verified.

0. Facts

List every checkable unit in the draft: figures, dates, titles, names, quoted strings.

For each, one of three statuses:

status means
verified primary source found, matches
unverified needs a source before publication
diverges a discrepancy was found — name it

Rules that override convenience:

  • A quoted string is verbatim or it is not a quote. Never join two fragments of a source inside one set of quotation marks
  • "Plausible" is not a status. Either a source exists or the unit is unverified
  • A figure carrying now, today, or currently is re-checked at publication time, not taken from an old draft
  • Technical detail invented to sound right — a method, a format, a tool name that is not in the source — is diverges, not unverified

One diverges, or one unverifiable quotation, and the check stops here.

1. Claims

Load every claim page. Split by state.

For status: rule — does the draft contradict it? If yes, this is a blocking objection. Quote the line, name the claim, give the replacement.

For status: candidate — report as a note. Say n out loud: "two runs, not three." Never block on it. A candidate that blocks is the failure this whole repo is built to prevent.

For status: retired — if the draft relies on one, say so plainly and give the reason it was retired. Retired claims are kept precisely so this can happen.

2. Contract

Whatever your domain's output contract is, check it here. The agent writes this section during setup — it is the only part of this skill that is domain-specific.

3. Report

FACTS
[table, or STOP with the reason]

BLOCKING
[quoted line -> which rule -> replacement, or "none"]

NOTES
[candidate-state observations, each with its n]

VERDICT
[ship / fix / rebuild]

Read the full file on GitHub · 83 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. 7d ago First seen · 83 lines · 64 tokens per session scan A 7a7770c1417c

Subscribe to this mod's changes

wiki-check is a skill published in the GitHub repository helicerat/llm-wiki-loop (6 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 692 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-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