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/treylom/knowledge-manager/agents-mdgit clone --depth 1 https://github.com/treylom/knowledge-managerWhat 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 | $0.02139 | $0.02139 |
| Opus 5 | $0.01069 | $0.01069 |
| Sonnet 5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
knowledge-manager 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 yesterday.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Generic AI agent contract
This file is the vendor-neutral version of
CLAUDE.md. If you are an AI coding assistant other than Claude Code (e.g. Codex, Cursor, Gemini, Antigravity, OpenCode, an autonomous agent framework, or a future model), read this file before you modify anything in this repository.
Repository Identity
- Name: knowledge-manager
- Type: Claude Code / Antigravity skill + agent + command distribution repo
- Primary purpose: Ingest content (web, PDF, YouTube, social, chat logs) and file it as structured notes in the user's Obsidian vault (or Notion, or local markdown).
- Deployment model: Users
git clonethis repo, run a setup wizard, and the wizard rewrites placeholder tokens in every skill file with the user's personal paths. - Key invariant: The committed source tree is portable. It contains
{{PLACEHOLDER}}tokens, never one user's hardcoded paths.
Read First
Read these files in this order before making any edit:
CLAUDE.md— the same contract written for Claude Code, with a worked example of source-vs-substituted file forms.README.md— end-user documentation; see the## Installation & Configurationsection for how the placeholder system is presented to users.docs/vault-path-configuration.md— full technical reference: config schema, substitution algorithm, skip-worktree mechanism, troubleshooting.
If you are unable to read those files for any reason, stop and ask the user to paste their contents rather than guessing.
Placeholder Contract (CRITICAL)
The following 5 tokens appear verbatim in committed source files and must be preserved whenever you edit a skill, agent, or command file:
| Token | Semantic meaning |
|---|---|
{{VAULT_PATH}} |
Absolute path to the user's Obsidian vault directory |
{{VAULT_NAME}} |
Basename of {{VAULT_PATH}} (the vault folder name, used by Obsidian CLI --vault argument) |
{{OBSIDIAN_CLI}} |
Absolute path to the Obsidian CLI executable (may be empty string if not installed) |
{{ZETTELKASTEN_ROOT}} |
Vault-relative path to the Zettelkasten root folder (default: Zettelkasten) |
{{RESEARCH_ROOT}} |
Vault-relative path to the research/MOC root folder (default: Research) |
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.
- yesterday First seen · 170 lines · 2,139 tokens per session scan A 956e8c3ec8d0
knowledge-manager AGENTS.md is an instructions file published in the GitHub repository treylom/knowledge-manager (227 stars, last pushed yesterday), licensed MIT. It adds 2,139 tokens to every session, about $0.0107 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 2026-09-01.
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.
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.
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).
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.