agentmods.dev

TheKnowledge CLAUDE.md

A project instruction file for TheKnowledge, a personal knowledge base built from Markdown files and connected tools. It defines what agents may change, where canonical content lives, and which guides and gateway processes govern edits.

In plain words
What is it for?
It is for guiding work on the knowledge base, including reading content, checking its status, importing sources, and proposing updates through the approved gateway.
Why use it?
It prevents agents from changing the knowledge base through the wrong path or ignoring its rules for sources, citations, and content management.

Instructions file

23 1mo ago A scan 4,608 tokens original MIT
View the source file badwally/TheKnowledge
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 instructions/badwally/theknowledge/claude-md
Clone the repo
git clone --depth 1 https://github.com/badwally/TheKnowledge
Per session 4,608 This file is loaded in full into every session.
When invoked 4,608 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.04608 $0.04608
Opus 5 $0.02304 $0.02304
Sonnet 5 $0.00922 $0.00922
Haiku 4.5 $0.00461 $0.00461

Measured 2d ago against content hash 3e3eb8330777, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TheKnowledge 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 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.

CLAUDE.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

~/code/knowledge/ — Personal Knowledge Base

Canonical knowledge base for all ~/code/* projects. Implements the LLM Wiki pattern (Karpathy gist 442a6bf555914893e9891c11519de94f) with three load-bearing integrations:

  • The wiki (this repo) is canonical — markdown + YAML frontmatter, citation-graph enforced by the gateway.
  • NotebookLM is the heavy-synthesis service called through the gateway (wiki nlm-*); artifacts file back to wiki/artifacts/.
  • Obsidian is the knowledge-graph visualization engine on top of the vault — same wikilink format, same markdown.

This file is the agent control surface. WIKI.md is the conventions reference. Read WIKI.md before designing converters, page types, gateway operations, validator rules, or editorial policies. Read index.md and run wiki status to orient on live content. For human-facing usage, read TUTORIAL.md. For per-milestone delivery history, read BUILD.md § 9.

What you may do here

  • Read any file in wiki/, raw/, nlm/, index.md, log.md. Reading is unrestricted.
  • Propose wiki updates and source ingests only via the gateway — never write directly to wiki/ or raw/.
  • Read sources to answer questions, then file good answers back into the wiki via wiki query, which writes the answer as a wiki page.
  • Cite into the wiki from any other ~/code/* project — wiki paths are stable references.

Hard rules (no exceptions)

  1. No direct writes to wiki/ or raw/. All writes go through the gateway: wiki <subcommand> (CLI) or wiki_* (MCP). Direct file writes are caught by the validator and git diff review.
  2. No direct calls to nlm or NotebookLM MCP tools. All NotebookLM operations go through the gateway. The gateway guarantees every NotebookLM artifact is filed back to the wiki with bidirectional links — Discipline Gate.
  3. Citation grounding is mandatory. Every claim in every wiki page must be followed by [[sources/<id>]] linking to the source page. Validator rejects pages with claims lacking provenance. Exception: pages written with --draft are committed with draft: true and the rule is downgraded to a lint warning until wiki finalize is run. Drafts older than 7 days are flagged in lint.
  4. Lookup before create. Search index.md and existing pages before creating a new entity or concept. Validator warns on slug similarity.
  5. Plan before write. For any incremental ingest, produce a written plan in your response: pages you will create, pages you will update, cross-references you will add. Gateway logs the plan to log.md.
  6. Sources in raw/ are immutable. Frontmatter may be updated by pipeline stages (filter score, NotebookLM corpus IDs, wiki backlinks). Body content is never modified after ingest.

Read the full file on GitHub · 206 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.

  1. 2d ago First seen · 206 lines · 4,608 tokens per session scan A 3e3eb8330777

Subscribe to this mod's changes

TheKnowledge CLAUDE.md is an instructions file published in the GitHub repository badwally/TheKnowledge (23 stars, last pushed 1mo ago), licensed MIT. It adds 4,608 tokens to every session, about $0.0230 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.

Memory and contextWriting and docs
Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens