llm-wiki: Command for Claude Code

.claude/commands/wiki-synthesize.md

wiki-synthesize is a command for Claude Code from Pratiyush/llm-wiki. It costs 0 tokens per session (537 once invoked), scanned A, original, MIT.

A command for turning raw Claude Code session transcripts into summary pages in an LLM wiki. An LLM wiki is a linked collection of documents that organizes information from those sessions.

In plain words
What is it for?
It helps synthesize new or existing transcript sources, preview changes without writing them, estimate work, check the language-model backend, list pending prompts, and complete a queued synthesis.
Why use it?
It reduces the manual work of reading transcripts and keeping source summaries up to date, while offering previews, estimates, checks, and pending-work handling.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Pratiyush/llm-wiki's own configuration. It tells Claude Code how to work on llm-wiki 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 configures →

Part of the llm-wiki plugin — 6 skills, 18 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Pratiyush/llm-wiki. 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/Pratiyush/llm-wiki/master/.claude/commands/wiki-synthesize.md
Clone the repo
git clone --depth 1 https://github.com/Pratiyush/llm-wiki

Made for: Claude Code.

Or install llm-wiki, the plugin that ships this one along with the rest of its 6 skills, 18 commands.

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-synthesize

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/pratiyush/llm-wiki/wiki-synthesize"><img src="https://agentmods.dev/badge/commands/pratiyush/llm-wiki/wiki-synthesize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 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 $0.00000 $0.00537
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00054

Measured 10d ago against content hash 26eb59910f3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wiki-synthesize 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.

.claude/commands/wiki-synthesize.md · 52 lines

What it actually says

Synthesize wiki/sources/<slug>.md pages from raw session transcripts using the configured LLM backend.

Wraps: python3 -m llmwiki synthesize

Usage: /wiki-synthesize or any natural-language variant. Claude translates the phrasing into flags.

Natural-language → flags

You say Runs
"just show me what it would cost" python3 -m llmwiki synthesize --estimate
"preview without writing" python3 -m llmwiki synthesize --dry-run
"check the backend is reachable" python3 -m llmwiki synthesize --check
"force re-synthesize everything" python3 -m llmwiki synthesize --force
"synthesize but don't touch my wiki yet" python3 -m llmwiki synthesize --dry-run
"list pending agent prompts" / "what's waiting on me?" python3 -m llmwiki synthesize --list-pending
"complete pending synthesis <uuid>" python3 -m llmwiki synthesize --complete <uuid> --page <path> (body via --body or stdin)

Expected output

First run on a fresh corpus (dummy backend):

Backend: DummySynthesizer
Scanned 785, new 785, synthesized 785, skipped 0
  synthesized: proj-a → 2026-04-17-slug-1
  …

Re-run on unchanged tree:

Backend: DummySynthesizer
Scanned 785, new 0, synthesized 0, skipped 0

When to use

  • After /wiki-sync produces new raw/sessions/*.md files and you want their wiki/sources/*.md counterparts immediately.
  • After updating the prompt template under wiki/prompts/source_page.md — pair with --force to re-synthesize everything using the new prompt.
  • After switching synthesis backends (dummyollama → api).
  • Tutorial 08 — Synthesize with Ollama
  • /wiki-build — regenerates the static site after synthesize.
  • /wiki-lint — finds pages with empty tags / broken wikilinks after synthesize.
  • #50 (prompt-cache scaffold) · #315 (Claude API backend, in progress)
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. 10d ago First seen · 52 lines · 0 tokens per session scan A 26eb59910f3a

Subscribe to this mod's changes

wiki-synthesize is a command published in the GitHub repository Pratiyush/llm-wiki (387 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 537 tokens. 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 2026-08-30.