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/ghadisaab/ctx-memory/claude-mdgit clone --depth 1 https://github.com/GhadiSaab/ctx-memoryWrote 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/ghadisaab/ctx-memory/claude-md)<a href="https://agentmods.dev/instructions/ghadisaab/ctx-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/ghadisaab/ctx-memory/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 | $0.01711 | $0.01711 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
ctx-memory 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A fully local CLI tool giving coding agents (Claude Code, Codex, Gemini CLI, OpenCode) persistent memory across sessions. When a new session starts in a project, the agent automatically knows what was worked on before, what decisions were made, what errors were hit, and what files were touched — without re-explaining anything. Zero cloud, zero telemetry. Everything lives in ~/.ctx-memory/store.db.
End-to-end flow:
- Shell wrapper intercepts
claude(or codex/gemini/opencode), detects project via git remote/path, sets env vars, spawns real agent as child process - MCP server starts alongside — injects a tiny context header (~30 tokens), exposes
search_context()andget_project_memory()tools - During session: hooks fire on every tool call (file edits, bash commands, etc.), messages buffered in memory
- On session end (clean/Ctrl-C/crash): Layer 1 → Layer 2 → Layer 3 pipeline runs, embedding stored, next session can retrieve all of it
Build Plan Status
Step 1 ✅ Project scaffold + dependencies
Step 2 ✅ Shared types
Step 3 ✅ Database layer (schema, CRUD, vector search, orphan sweep)
Step 5 ✅ Structural feature extractor
Step 6 ✅ Keyword scorer + dictionaries
Step 7 ✅ Positional analyzer
Step 8 ✅ Pattern detector
Step 9 ✅ TF-IDF keyword extractor
Step 10 ✅ Tool event classifier
Step 11 ✅ Weight combiner → Layer1Output
Step 12 ✅ Layer 2 digest generator
Step 13 ✅ Layer 3 project memory merger
Step 14 ✅ Embedding: MiniLM + sqlite-vec
Step 15 ✅ MCP server (5 tools + session end handler) — src/mcp/handlers.ts + src/mcp/index.ts
Step 16 ✅ Integration test — tests/integration/session.test.ts
Step 17 ✅ Shell wrapper — src/wrapper/{detect,project,index}.ts
Step 18 ✅ Per-tool hook plugins — src/hooks/{receiver,claude,gemini,opencode,index}.ts
Step 19 ✅ CLI wizard — src/cli/index.ts (detectInstalledTools, createWrapperSymlink, injectPathLine, forgetProject, getAllProjects + bin entry)
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.
- 3d ago First seen · 139 lines · 1,711 tokens per session scan A 834f55b6834c
ctx-memory CLAUDE.md is an instructions file published in the GitHub repository GhadiSaab/ctx-memory (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,711 tokens to every session, about $0.0086 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.
Other instructions, from other repositories
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
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).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.