agentmods.dev

llm-wiki-source-refresh

llm-wiki-source-refresh is a skill for Claude Code, Codex from po4yka/llm-wiki-skills. It costs 52 tokens per session (570 once invoked), scanned A, original, MIT.

A source-checking workflow for LLM-Wiki pages, which are documented knowledge pages backed by sources. It finds stale claims or broken links and prepares a report or proposed correction.

In plain words
What is it for?
Use it to review pages after their freshness date, recheck changing facts, verify source links, and prepare report-only or patch-based updates.
Why use it?
It helps prevent old or unsupported information from being treated as current. It also shows what changed without silently rewriting the page.

Skill for Claude CodeCodex

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

not rated 3repo 18d ago A scan 52 tokens original MIT

Good fit Use it to review pages after their freshness date, recheck changing facts, verify source links, and prepare report-only or patch-based updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/po4yka/llm-wiki-skills/llm-wiki-source-refresh
View source ↗ po4yka/llm-wiki-skills
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-source-refresh
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-source-refresh

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-source-refresh"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-source-refresh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 570 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 $0.00052 $0.00570
Opus 5 $0.00026 $0.00285
Sonnet 5 $0.00010 $0.00114
Haiku 4.5 $0.00005 $0.00057

Measured 11d ago against content hash dd52f215b00f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

llm-wiki-source-refresh 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.

skills/llm-wiki-source-refresh/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM-Wiki Source Refresh

Goal

Refresh stale source-backed claims without silently rewriting truth.

When to use

  • A page's stale_after date has passed.
  • wiki-lint flagged stale or unsupported claims that need re-verification.
  • A source URL referenced by a wiki page appears dead or has moved.
  • Ecosystem/tool facts on a page may have changed since updated was last set.
  • Someone requests a freshness pass over a set of pages before citing them elsewhere.

Inputs

  • Target pages, source pages or lint report.
  • stale_after, updated, source_urls and source_paths fields.
  • Desired mode: report-only, patch proposal or approved patch.

Procedure

1. Identify stale targets

Find pages where:

  • stale_after is in the past;
  • source URLs no longer resolve;
  • current ecosystem/tool claims are older than the user's freshness window;
  • wiki-lint reported stale or unsupported claims.

2. Re-check sources

For current external claims, browse and cite fresh primary sources. For local sources, compare file hashes when available.

3. Classify change

Use:

Status Meaning
unchanged Existing claim still appears supported.
updated Source changed but conclusion remains close.
contradicted Fresh source conflicts with wiki claim.
missing Source unavailable or evidence not found.
needs-human Interpretation requires review.

4. Create refresh report

Use references/templates/reports/source-refresh-report.md when available.

5. Propose patches

Only propose patches by default. Mark contradicted or missing evidence for human review.

Output

## Source refresh summary

## Pages checked

## Fresh sources used

## Claims unchanged

## Claims updated

## Claims contradicted or missing

## Proposed patches

## Review required

Safety gates

  • Always browse for current external facts.
  • Do not silently rewrite verified pages.
  • Do not treat generated summaries as fresh sources.
  • Do not auto-resolve contradictions.
  • Do not refresh sensitive sources through external services without approval.

Read the full file on GitHub · 94 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. 11d ago First seen · 94 lines · 52 tokens per session scan A dd52f215b00f

Subscribe to this mod's changes

llm-wiki-source-refresh is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 52 tokens to every session and 570 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.

Claude CodeResearchWriting and docsagent-skillsai-agentscodexknowledge-managementllm-wiki
Related

Other skills, from other repositories

okf-harness-bootstrap

This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.

pumblus/okf-harness · 0 tokens

okf-harness

One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.

pumblus/okf-harness · 0 tokens

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

meta-sync-template

Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…

tboome33/obsidian-mcp-router · 159 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