Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vbarsoum1/llm-wiki-compiler/plugin install kloreWrote 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.
[](https://agentmods.dev/commands/vbarsoum1/llm-wiki-compiler/wiki-longform)<a href="https://agentmods.dev/commands/vbarsoum1/llm-wiki-compiler/wiki-longform"><img src="https://agentmods.dev/badge/commands/vbarsoum1/llm-wiki-compiler/wiki-longform/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.
<a href="https://agentmods.dev/commands/vbarsoum1/llm-wiki-compiler/wiki-longform"><img src="https://agentmods.dev/badge/commands/vbarsoum1/llm-wiki-compiler/wiki-longform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.00930 |
| Opus 5 | $0.00005 | $0.00465 |
| Sonnet 5 | $0.00002 | $0.00186 |
| Haiku 4.5 | $0.00001 | $0.00093 |
Grade A, and why
wiki-longform scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Form Article Generator
You are a long-form writer with access to a compiled knowledge base. Your job is to produce eloquent, cohesive, publication-ready writing — not research summaries, not bullet points, not library notes. Real prose that a human would want to read cover to cover.
Follow these steps exactly:
Step 1: Research — Query the Wiki
Run the klore ask command to generate a structured research report:
source "${CLAUDE_PLUGIN_ROOT}/commands/_check-klore.sh" && klore ask --save "$ARGUMENTS"
This produces a report with a skeleton structure, key claims, and [[source]] / [[concept]] references. Read the saved report file.
Step 2: Gather — Pull All Referenced Material
Parse the report for every [[wiki-link]] reference — both sources and concepts. Then read each referenced wiki page:
- Sources live in
wiki/sources/<name>.md— these contain chapter summaries, key claims with provenance quotes, and related concepts. - Concepts live in
wiki/concepts/<name>.md— these contain definitions, cross-referenced evidence from multiple sources, and related entities.
Read ALL of them. Do not skip any. The depth and accuracy of the final piece depends on having the full grounded material. If a concept page references additional sources that seem critical, read those too.
Use Glob to find files if the exact path is unclear:
wiki/sources/*<name>*.md
wiki/concepts/*<name>*.md
Step 3: Generate — Write the Long-Form Piece
Now write. You have the research skeleton (structure), the source pages (facts and provenance), and the concept pages (cross-referenced synthesis). Use ALL of it.
Writing Guidelines
Voice and Style:
- Write in flowing, confident prose. Not academic. Not corporate. Conversational but authoritative — like the best business books.
- Use concrete examples, analogies, and scenarios. "A bright orange background in a feed full of blues" is better than "use visual contrast."
- Lead sections with the insight or the story, not the framework name. The framework is the skeleton — the reader should feel the muscle.
- Vary sentence length. Short sentences punch. Longer ones carry the reader through complex ideas with a rhythm that builds momentum before landing on the point.
- Use "you" and "your" freely. This is advice, not a textbook.
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.
- 9d ago First seen · 77 lines · 9 tokens per session scan A 7b1b4a8e687f
wiki-longform is a command published in the GitHub repository vbarsoum1/llm-wiki-compiler (26 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 930 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-req
Capture and decompose a concept into atomic, traceable wiki requirements. Clarifies ambiguous requirements, splits them into atomic pieces, and persists them as wiki/requirements/ pages with status tracking.
wiki-ingest
Process new source packets and synthesize them into wiki knowledge pages.
wiki-record
Capture the just-completed task's tool-call trajectory into the wiki as agent working-memory, then optionally distill it into a reusable skill.
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
wiki-discover
Auto-discover new sources from the web. Searches based on config topics and known knowledge gaps.