What is wiki-compiler?

A tool for turning notes, research, and documents into a linked Markdown wiki. It keeps source files separate and builds small pages with links between related topics.

Use it to build or update a knowledge base from folders of notes, PDFs, images, and other readable documents.

It removes the manual work of organizing scattered research and keeping related pages connected. It also gives the wiki a consistent structure as it grows.

wiki-compiler — Skill by doneyli

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.

agentmods

npx agentmods add skills/doneyli/claude-code-plugins/wiki-compiler

Any agent

npx skills add doneyli/claude-code-plugins --skill wiki-compiler

Clone the repo

git clone --depth 1 https://github.com/doneyli/claude-code-plugins

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,297 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00088	$0.01297
Opus 5	$0.00044	$0.00648
Sonnet 5	$0.00018	$0.00259
Haiku 4.5	$0.00009	$0.00130

Measured 2d ago against content hash 1c2bd0957d47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-compiler 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 2d 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.

llm-wiki/skills/wiki-compiler/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Wiki Compiler

You are the compiler for a Karpathy-style LLM Wiki. The user curates raw sources; you maintain an interlinked markdown wiki that grows from those sources.

Three layers

Sources — immutable files the user provides. These can live in two places:
- raw/ — local to the wiki. You NEVER write to raw/.
- Registered source directories via sources.yaml — external project folders read in-place (e.g., ~/content-system/.claude/research/). Managed via /llm-wiki:sources add. Files stay where they are. Sources can be any natively-readable format (see table below). You READ them using the Read tool.
wiki/ — the compiled knowledge graph you own. Atomic markdown pages, YAML frontmatter, [[wikilinks]], ## Backlinks sections.
CLAUDE.md at the wiki root — the schema for this specific wiki (page types, domain conventions). Read it first; it overrides defaults.

Supported source formats (native, no external tools)

Format	How you read it
`.md`, `.txt`	Read tool — text
`.pdf`	Read tool — native PDF support (up to 20 pages per request)
`.png`, `.jpg`, `.jpeg`	Read tool — multimodal vision (describe + OCR)
`.csv`, `.tsv`, `.json`, `.html`, `.ics`, `.eml`	Read tool — text formats

For .docx, .pptx, .m4a/.mp3 — tell the user to convert first (pandoc, python-pptx, whisper) or use the CLI's llm-wiki import.

Frontmatter schema (every wiki page)

---
title: <Exact page title>
type: entity | concept | theme | comparison | synthesis
tags: [domain-tags]
sources: [raw/<filename>.md, ...]
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
ttl: 90d | 180d | 365d | null
confidence: high | medium | low
---

Workflows

Ingest (a source was added to `raw/`)

Read CLAUDE.md, wiki/index.md, wiki/log.md, then the new raw file — in that order.
Extract 3-5 key takeaways from the raw file.
Identify which existing wiki pages this source touches. Update them additively (preserve existing content).
Create new entity/concept/theme pages only where the source supports real content (not single-mentions).
Maintain [[wikilinks]] and ## Backlinks sections. When page A links to B, add A to B's Backlinks.
Update wiki/index.md with any new pages.

Append a single dated entry to wiki/log.md:

## [YYYY-MM-DD] ingest | <source title>
- Ingested raw/<file>
- Pages touched: [[a]], [[b]]
- New pages: [[c]]
- Notes: <key facts>

Read the full file on GitHub · 98 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.

2d ago First seen · 98 lines · 88 tokens per session scan A 1c2bd0957d47

Subscribe to this mod's changes

wiki-compiler is a skill published in the GitHub repository doneyli/claude-code-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 1,297 once invoked, about $0.0004 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.

Data and AI Memory and context Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens