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/guachoxx/claude-memory-framework/claude-mdgit clone --depth 1 https://github.com/guachoxx/claude-memory-frameworkWrote 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/guachoxx/claude-memory-framework/claude-md)<a href="https://agentmods.dev/instructions/guachoxx/claude-memory-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/guachoxx/claude-memory-framework/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 | $0.00912 | $0.00912 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade C, and why
claude-memory-framework CLAUDE.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- User identity and provider settings live in claude-memory/CONFIG.md (gitignored). See claude-memory/providers/ for setup instructions. When current_user is not set, the framework operates in single-user mode. --> How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Memory Index
System Overview
Configuration
Quick Navigation
| I need to... | Read |
|---|---|
| Understand the architecture | ARCHITECTURE document |
| Credentials, endpoints, connection | CREDENTIALS document |
| Build commands | BUILD COMMANDS document |
| Testing methodology | TESTING METHODOLOGY document |
| Conventions and memory rules | CONVENTIONS document |
| Reusable technical lessons | LESSONS LEARNED document |
| See active projects and status | Project index |
| Available providers | claude-memory/providers/ |
| Provider-specific setup | claude-memory/providers/{provider}/SETUP.md |
| Full documentation for humans | HUMANS_START_HERE.md |
| Multi-user setup | CONVENTIONS → "Multi-User Mode" |
| Provider cache (external providers) | claude-memory/PROVIDER_CACHE.md |
Provider note: Where each document lives depends on the configured provider. See
claude-memory/providers/for details.
Boot Sequence
- Read this file (
CLAUDE.md) — you are here - Read
claude-memory/CONFIG.md— provider type, user identity, connection - Read CONVENTIONS (from provider) — framework operational rules. Mandatory on every session.
- Read
claude-memory/PROVIDER_CACHE.md— cached entity IDs (warm start) or discover provider structure (cold start) - Read Project Index — overview of active projects (names, statuses, owners). Do NOT read individual project CURRENT STATUS pages at this point.
- Ready to work. Read a project's CURRENT STATUS only when the user asks to work on it.
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 · 67 lines · 912 tokens per session scan C 16d73e3966ec
claude-memory-framework CLAUDE.md is an instructions file published in the GitHub repository guachoxx/claude-memory-framework (3 stars, last pushed 6mo ago), licensed Unlicense. It adds 912 tokens to every session, about $0.0046 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
SecureContext CLAUDE.md
Instructions for iampantherr/SecureContext, covering securecontext — agent instructions, what this project is, directory layout, build commands and 13 mcp tools.
consolidate-memory AGENTS.md
AGENTS.md instructions for Zenetusken/consolidate-memory, covering agents.md — consolidate-memory, what this is, commands you will actually run, layout and core contracts — do not break these.
consolidate-memory CLAUDE.md
Claude Code instructions for Zenetusken/consolidate-memory, covering consolidate-memory — project conventions, the one gotcha that matters, layout, conventions and safety (this repo is public).
aictx AGENTS.md
Instructions for oldskultxo/aictx, covering agents instructions for aictx and ai context engine.
aictx aictx.instructions.md
Instructions for oldskultxo/aictx: Apply these instructions to repository work. Prefer AICTX MCP tools when available; fall back to AICTX CLI commands otherwise. They intentionally duplicate the minimal AICTX lifecycle because Copilot support varies by surface.
prodkit CLAUDE.md
Instructions for ramybarsoum/prodkit, covering prodkit - schema, knowledge architecture, layer 1: raw sources (user-owned, immutable), layer 2: the wiki (llm-owned, compounding) and links.