agentmods.dev

packmind CLAUDE.md

packmind CLAUDE.md is an instructions file for coding agents from mchl-schrdng/packmind. It costs 1,014 tokens per session, scanned A, original, Apache-2.0.

Project instructions for PackMind, a Node and TypeScript command-line tool that stores project memory, tracks token and cost use, recalls information locally, and applies development guardrails. They describe its commands, folder structure, build process, tests, and coding rules.

In plain words
What is it for?
Use them when building, testing, auditing, or modifying PackMind, including its command-line commands, lifecycle hooks, local recall, and MCP server.
Why use it?
They give an agent the project-specific details needed to edit PackMind safely and run the same checks expected by the project. This reduces mistakes caused by using the wrong commands or changing code in the wrong place.

Instructions file

not rated 2 1mo ago A scan 1,014 tokens original Apache-2.0
View the source file mchl-schrdng/packmind
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/mchl-schrdng/packmind/claude-md
Clone the repo
git clone --depth 1 https://github.com/mchl-schrdng/packmind

Wrote 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.

agentmods badge for packmind CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mchl-schrdng/packmind/claude-md.svg)](https://agentmods.dev/instructions/mchl-schrdng/packmind/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mchl-schrdng/packmind/claude-md"><img src="https://agentmods.dev/badge/instructions/mchl-schrdng/packmind/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,014 This file is loaded in full into every session.
When invoked 1,014 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 $0.01014 $0.01014
Opus 5 $0.00507 $0.00507
Sonnet 5 $0.00203 $0.00203
Haiku 4.5 $0.00101 $0.00101

Measured 5d ago against content hash b216ce121e1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

packmind 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 5d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PackMind

A second brain for Claude Code: project memory, real token & cost accounting, local semantic recall, and active guardrails - delivered as lifecycle hooks plus an MCP server. Published to npm as packmind (Apache-2.0).

Stack

  • Node ≥20, TypeScript, ESM. Package manager: pnpm.
  • Tests: Vitest. No runtime framework - the CLI is plain commander.
  • Runtime deps: @modelcontextprotocol/sdk, chalk, commander, ignore. Optional: @xenova/transformers (local embeddings; recall only).

Commands

  • pnpm build - compiles twice: tsc (ESM lib → dist/) and tsc -p tsconfig.hooks.json (hooks → CommonJS dist/hooks/). Both must pass.
  • pnpm test - Vitest suite. pnpm test:coverage - coverage + report.
  • pnpm audit --prod --audit-level=high - what CI gates on.
  • Run the built CLI: node dist/bin/packmind.js <cmd>.

Architecture (src/)

  • bin/, cli/ - entrypoint and one file per command (init, scan, status, insights, recall-cmd, backup-cmd, maintain-cmd, doctor, mcp-cmd, …).
  • hooks/ - the 7 standalone lifecycle hooks + runtime.ts (see rules below).
  • mcp/ - MCP stdio server (server.ts) and tool handlers (tools.ts).
  • state/ - formats.ts (CRLF-safe map/knowledge parsers), schema.ts (config
    • deep-merge), mapper.ts (the file map), snapshot.ts (backup/restore), walk.ts, project.ts.
  • cost/ - estimator.ts (local), exact.ts (Anthropic count-tokens), pricing.ts, ledger.ts, insights.ts.
  • recall/ - local embeddings (embedder.ts), vector store, chunker, indexer.
  • compress/ - store.ts: content-addressed store for shelved non-source blobs (store/retrieve/compact), backing the compress/retrieve MCP tools.
  • guard/ - secrets.ts, path-guard.ts, policy.ts.
  • adapters/claude-code.ts - registers hooks + the MCP server into a project.
  • dashboard/ - loopback web dashboard: server.ts + config-api.ts; the HTML lives at templates/dashboard.html (served via TEMPLATES_DIR).
  • templates/ - files seeded into a consuming project's .packmind/.

Read the full file on GitHub · 65 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. 5d ago First seen · 65 lines · 1,014 tokens per session scan A b216ce121e1d

Subscribe to this mod's changes

packmind CLAUDE.md is an instructions file published in the GitHub repository mchl-schrdng/packmind (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,014 tokens to every session, about $0.0051 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 2026-08-31.

Memory and contextaiclaudeclaude-codeclideveloper-toolsembeddings
Related

Other instructions, from other repositories

llm-wiki-memory AGENTS.md

Instructions for ctxr-dev/llm-wiki-memory, covering agents.md, development discipline (.agents/), layout, tests and conventions.

ctxr-dev/llm-wiki-memory · 2,138 tokens

ClawMem AGENTS.md

Instructions for yoloshii/ClawMem, covering clawmem — agent quick reference, inference at a glance, install, or step by step and memory retrieval (90/10 rule).

yoloshii/ClawMem · 7,138 tokens

engram-mcp CLAUDE.md

Claude Code instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.

edg-l/engram-mcp · 7,648 tokens

palaia AGENTS.md

AGENTS.md instructions for byte5ai/palaia, covering agent instructions, git workflow, pull requests, project and pre-push hook.

byte5ai/palaia · 735 tokens

Axon copilot-instructions.md

Copilot instructions for jyunming/Axon, covering axon knowledge center — copilot instructions, what axon is, project namespaces, hierarchical projects (up to 5 levels) and merged read-only scopes.

jyunming/Axon · 4,209 tokens

subcog CLAUDE.md

Instructions for zircote/subcog, covering claude.md, project overview, key capabilities, build commands and primary development workflow.

zircote/subcog · 501 tokens