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.
npx agentmods add instructions/bradduy/wiki-knowledge-compiler/claude-mdgit clone --depth 1 https://github.com/bradduy/wiki-knowledge-compilerWrote 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/instructions/bradduy/wiki-knowledge-compiler/claude-md)<a href="https://agentmods.dev/instructions/bradduy/wiki-knowledge-compiler/claude-md"><img src="https://agentmods.dev/badge/instructions/bradduy/wiki-knowledge-compiler/claude-md.svg" alt="Measured on agentmods" 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 | $0.01688 | $0.01688 |
| Opus 5 | $0.00844 | $0.00844 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
wiki-knowledge-compiler CLAUDE.md 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Knowledge Compiler — LLM Wiki Plugin
You are operating inside the wiki-knowledge-compiler plugin, a local-first knowledge compiler for Claude Code.
Core Principles
raw/is immutable. Never modify, rename, or delete files inraw/. It is the source of truth.- Provenance is mandatory. Every derived page (summary, concept, topic, insight) must cite its source(s) from
raw/or other wiki pages. Never fabricate citations. - Uncertainty must be explicit. If a claim is inferred, speculative, or partially supported, mark it with
[uncertainty: reason]. Never present uncertain information as fact. - Write-back discipline. Useful outputs belong in the knowledge base, not just in conversation. If you generate a reusable answer, summary, or insight, write it to the appropriate directory.
- Markdown-first. All knowledge is stored as plain markdown with YAML frontmatter. No proprietary formats, no databases required.
- No hallucinated structure. Only create pages when there is real content to put in them. Do not generate empty placeholder pages to fill out the wiki.
Knowledge Base Layout
raw/ # Immutable source documents (PDFs, notes, URL stubs)
wiki/ # All generated pages the user reads and browses
.data/ # Hidden internal working data:
index/ # Master index, concept index, source index
log.md # Append-only activity log
summaries/ # Per-source summaries with provenance
concepts/ # Atomic concept pages
topics/ # Broader topic groupings
insights/ # Cross-cutting observations
entities/ # Knowledge graph — people, projects, technologies, decisions
references/ # External reference stubs
drafts/ # Work-in-progress pages
Knowledge Graph
The wiki maintains a knowledge graph as typed markdown pages in .data/entities/. During ingestion, named entities (people, projects, libraries, technologies, decisions) are extracted and connected with typed relationships.
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.
- 5d ago First seen · 127 lines · 1,688 tokens per session scan A 694d2a8a55dd
wiki-knowledge-compiler CLAUDE.md is an instructions file published in the GitHub repository bradduy/wiki-knowledge-compiler (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,688 tokens to every session, about $0.0084 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.