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/webrenew/memories/claude-mdgit clone --depth 1 https://github.com/webrenew/memoriesWrote 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/webrenew/memories/claude-md)<a href="https://agentmods.dev/instructions/webrenew/memories/claude-md"><img src="https://agentmods.dev/badge/instructions/webrenew/memories/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 | $0.00458 | $0.00458 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
memories 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 4d 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.
What it actually says
CLAUDE.md
This document is public and intended for anyone forking or contributing to webrenew/memories, including human contributors and AI coding agents.
What This Repo Is
memories is a monorepo for the Memories platform:
packages/cli:@memories.sh/cli(CLI + local MCP server)packages/core: shared memory/storage logicpackages/ai-sdk: SDK helpers for app integrationpackages/web: Next.js app, API routes, docs, dashboardexamples/: starter integrations (Next.js, Express, Python)
Fork Quickstart
git clone https://github.com/<your-org>/memories.git
cd memories
pnpm install
cp .env.example .env.local
Run development servers:
# Web app
cd packages/web && pnpm dev
# CLI package
cd packages/cli && pnpm dev
Required Checks Before PR / Push
Run from repo root:
pnpm lint
pnpm typecheck
pnpm build
If your change affects runtime behavior, also run tests:
pnpm test
Contribution Expectations
- Keep PRs focused and small when possible.
- Do not commit secrets or local-only credentials.
- Prefer TypeScript and small, composable functions.
- Update docs/examples when API or CLI behavior changes.
- Preserve backward compatibility unless the change is explicitly breaking and documented.
Generated and Local Files
- Commit source changes, docs, and examples.
- Avoid committing personal scratch files or local machine artifacts.
- If a generated file is required by the repo build/docs pipeline, keep it in sync with the code that generates it.
Where To Start
- Product overview and setup:
README.md - Contributing process:
CONTRIBUTING.md - Security policy:
SECURITY.md - Web docs source:
packages/web/content/docs - Starter integrations:
examples/
Need Help?
- Open an issue: https://github.com/webrenew/memories/issues
- Start a discussion: https://github.com/webrenew/memories/discussions
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.
- 4d ago First seen · 76 lines · 458 tokens per session scan A 636cbcd19632
memories CLAUDE.md is an instructions file published in the GitHub repository webrenew/memories (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 458 tokens to every session, about $0.0023 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
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).