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/kenn-io/msgvault/claude-mdgit clone --depth 1 https://github.com/kenn-io/msgvaultWrote 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/kenn-io/msgvault/claude-md)<a href="https://agentmods.dev/instructions/kenn-io/msgvault/claude-md"><img src="https://agentmods.dev/badge/instructions/kenn-io/msgvault/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 | $0.04285 | $0.04285 |
| Opus 5 | $0.02142 | $0.02142 |
| Sonnet 5 | $0.00857 | $0.00857 |
| Haiku 4.5 | $0.00428 | $0.00428 |
Grade A, and why
msgvault 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 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
@CONSTITUTION.md
Feature Discovery
For uncertain new features, use these rules as a reasoning checkpoint. Do not create a design document merely to satisfy them.
- Start from the concrete user outcome and inspect the nearest real artifact or production path with safe, reversible checks.
- For local archives and importers, inspect schemas and aggregate metadata before recommending external services or indirect workflows. Do not display personal content or identifiers unless explicitly needed and authorized.
- Keep verified source capabilities, current msgvault support, workaround dependencies and trust costs, and unverified assumptions separate.
- Prefer the smallest bounded end-to-end vertical slice through the relevant production path. Treat only conditions blocking the next reversible step as prerequisites.
- When the user asks to contribute upstream and the contribution is uncertain, prefer a focused draft PR linked to the motivating issue. Defer unrelated hardening until evidence or feedback makes it necessary.
General Workflow
When a task involves multiple steps (e.g., implement + commit + PR), complete ALL steps in sequence without stopping. If creating a branch, committing, and opening a PR, finish the entire chain.
Always commit after every turn. Don't wait for the user to ask — if you made changes, commit them before responding. Do not ask "shall I commit?" or "want me to commit?" — just commit. Committing is not a destructive or risky action; it is the expected default after every change.
PR descriptions should be concise and changelog-oriented: what changed, why, and how to use it. Do not include test plans, design decisions, or implementation details — those belong in specs and commit messages.
Never name private downstream projects or other private codebases in public code, tests, fixtures, documentation, commit messages, pull requests, or issues. Describe the reusable requirement generically and run the private-data scrub before publishing.
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 Changed · +7 lines · +46 tokens per session 8f1d0926b427
- 3d ago First seen · 394 lines · 4,239 tokens per session scan A 18bbf0c961f1
msgvault CLAUDE.md is an instructions file published in the GitHub repository kenn-io/msgvault (2,047 stars, last pushed yesterday), licensed MIT. It adds 4,285 tokens to every session, about $0.0214 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.
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.