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/catchen/knowledge-wiki-template/agents-mdgit clone --depth 1 https://github.com/CatChen/knowledge-wiki-templateWhat 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 | $0.00737 | $0.00737 |
| Opus 5 | $0.00368 | $0.00368 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
knowledge-wiki-template AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base
This workspace is a personal knowledge base — a collection of Markdown notes and documents.
Search
The qmd MCP server is connected and indexes this entire folder as the knowledge collection. Use it for any search or lookup task:
qmd__query— search using asearchesarray of typed sub-queries. Three types:lex(BM25 keyword; supports"quoted phrase"and-negation),vec(semantic/meaning-based),hyde(hypothetical answer passage, 50-100 words). First sub-query gets 2× weight — combine types for best recall. Key params:intent(disambiguates query),minScore,limit(default 10).qmd__get— fetch a single document by path, docid (#abc123), or path with line offset (file.md:100). SupportsfromLine,maxLines,lineNumbers. Search results include alinefield — usefromLine: line-20, maxLines: 80to read surrounding context.qmd__multi_get— fetch multiple documents by glob pattern or comma-separated list. SupportsmaxBytes(skip large files; default 10 KB),maxLines,lineNumbers.qmd__status— check index health and document count.
Default behavior: When asked about something that might be in the notes, search qmd before answering from training knowledge. If qmd is unavailable or returns insufficient results, fall back to rg (ripgrep) to search the files directly.
Folder Conventions
| Folder | Contents |
|---|---|
Wiki/ |
AI-generated wiki — see below. Do not edit manually. |
Source folders (e.g. Notes/, Ideas/, Docs/) are defined by the repo owner. Treat any folder not listed above as user-maintained source content.
Wiki
The Wiki/ directory implements the LLM Wiki pattern: rather than re-synthesizing knowledge on every query, AI incrementally builds a persistent, interconnected set of markdown pages from the source documents. All content in Wiki/ is generated and maintained by the skills below — do not edit it manually.
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 · 37 lines · 737 tokens per session scan A 6d04b22aa8fa
knowledge-wiki-template AGENTS.md is an instructions file published in the GitHub repository CatChen/knowledge-wiki-template (105 stars, last pushed 2mo ago), licensed MIT. It adds 737 tokens to every session, about $0.0037 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
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 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).
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.
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).
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.
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.