knowledge-manager CLAUDE.md

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/treylom/knowledge-manager/claude-md

Clone the repo

git clone --depth 1 https://github.com/treylom/knowledge-manager

Per session 1,796 This file is loaded in full into every session.

When invoked 1,796 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.

Model	Per session	Once invoked
Fable 5	$0.01796	$0.01796
Opus 5	$0.00898	$0.00898
Sonnet 5	$0.00359	$0.00359
Haiku 4.5	$0.00180	$0.00180

Measured today against content hash dc3782a03d57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-manager 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 today.

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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Code project contract

This file is read automatically by Claude Code when it opens the knowledge-manager repo. It tells Claude how the placeholder system works and how to edit skill, agent, and command files without breaking portability for other users.

Repository purpose

knowledge-manager is a deployment repo. End users clone it, run /knowledge-manager-setup, and the wizard substitutes their personal paths into the skill/agent/command files. The source tree in this repo must stay portable — meaning it must contain {{PLACEHOLDER}} tokens, not one specific user's hardcoded vault path.

If you hardcode /home/tofu/AI/AI_Second_Brain (or any other personal path) into a skill file, every downstream user who pulls that change is broken until they manually reset it.

Critical: Placeholder System

Every file under skills/, agents/, commands/, and their .claude/ mirrors is either:

Pristine source (what lives in git) — contains placeholder tokens like {{VAULT_PATH}}.
Substituted local copy (what the user actually uses) — tokens replaced with real values from km-config.json, and marked git update-index --skip-worktree so the changes don't show up as dirty.

The 5 placeholders

Placeholder	Replaced with	Source config field
`{{VAULT_PATH}}`	Absolute vault path, e.g. `/home/user/Documents/MyVault`	`storage.obsidian.vaultPath`
`{{VAULT_NAME}}`	Basename of vault path, e.g. `MyVault`	(derived)
`{{OBSIDIAN_CLI}}`	Path to Obsidian CLI executable, or empty	`obsidianCli.path`
`{{ZETTELKASTEN_ROOT}}`	Vault-relative folder, e.g. `Zettelkasten`	`storage.obsidian.zettelkastenRoot`
`{{RESEARCH_ROOT}}`	Vault-relative folder, e.g. `Research`	`storage.obsidian.researchRoot`

Placeholders in source vs after setup

# IN SOURCE (what you commit):
Save the extracted note to {{VAULT_PATH}}/{{ZETTELKASTEN_ROOT}}/AI/note.md

# AFTER /knowledge-manager-setup (local user view):
Save the extracted note to /home/user/Documents/MyVault/Zettelkasten/AI/note.md

Read the full file on GitHub · 144 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.

today First seen · 144 lines · 1,796 tokens per session scan A dc3782a03d57

Subscribe to this mod's changes

knowledge-manager CLAUDE.md is an instructions file published in the GitHub repository treylom/knowledge-manager (227 stars, last pushed yesterday), licensed MIT. It adds 1,796 tokens to every session, about $0.0090 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.

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