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/cogniplex/codemem/claude-mdgit clone --depth 1 https://github.com/cogniplex/codememWhat 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 | $0.01355 | $0.01355 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
codemem 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 2d 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 — 100 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 when working with this repository.
Build & Test
cargo build # Build all crates
cargo test --workspace # Run all tests
cargo bench # Run benchmarks
cargo fmt --all -- --check # Check formatting
cargo clippy --workspace --all-targets -- -D warnings # Lint check
UI (uses Bun, not npm):
cd ui && bun install && bun run dev # Dev server
cd ui && bun run build # Production build → ui/dist/
cd ui && bun run tsc --noEmit # Type check
cd ui && bun run eslint . # Lint
cd ui && npx playwright test # E2E tests
CI uses RUSTFLAGS: -D warnings — all warnings are errors. Always run clippy before pushing.
Git Workflow
When working with git, always confirm the current branch before committing or pushing. Never assume you're on the correct branch.
Code Review
When asked to do code review, do a single thorough pass. Do not flip-flop on whether a bug exists or is fixed — if uncertain, re-read the code before answering.
General Principles
Do not over-engineer solutions. Apply only the changes requested. Do not add extra fields, workflows, or abstractions unless explicitly asked.
This is primarily a Rust project. Always run cargo test after making changes. Run cargo check before claiming code compiles cleanly.
When spawning sub-agents or waiting on background tasks, do NOT poll TaskList repeatedly. Check once, do other productive work, then check again after a reasonable interval.
Workspace Layout
6 crates: codemem-core (types/traits/errors/config) → codemem-storage (SQLite + HNSW + petgraph) + codemem-embeddings (Candle/Ollama/OpenAI) → codemem-engine (domain logic) → codemem (binary: CLI + MCP + REST API). Plus codemem-bench for benchmarks.
Development Quirks & Conventions
Storage method shadowing
Storage has concrete methods like list_sessions(namespace) (1-arg shorthand) AND StorageBackend trait methods like list_sessions(namespace, limit) (2-arg). Rust resolves concrete methods first. Be careful when code takes &dyn StorageBackend vs concrete Storage — the available method signatures differ.
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.
- 2d ago First seen · 100 lines · 1,355 tokens per session scan A 8b4dd0143bd9
codemem CLAUDE.md is an instructions file published in the GitHub repository cogniplex/codemem (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,355 tokens to every session, about $0.0068 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
engram-mcp CLAUDE.md
Instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.
trinity AGENTS.md
AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-08-24 15:26:38）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.
aionforge-memory AGENTS.md
Instructions for jscott3201/aionforge-memory, covering agent guide for aionforge memory, start here, workspace layout, core invariants and running locally.
palace-rs AGENTS.md
Instructions for AncientiCe/palace-rs, covering agent rules, 1. test-driven development (tdd), 2. quality gates on every task, 3. no plan markdown files and 4. internal api discipline.
ElBruno.MempalaceNet copilot-instructions.md
Instructions for elbruno/ElBruno.MempalaceNet, covering github copilot instructions for mempalace.net, installation, nuget package, cli tool and basic usage patterns.
simple-rick CLAUDE.md
Claude Code instructions for good-v1be/simple-rick, covering claude.md, what this is, tech stack, critical constraints and commands.