agentmods.dev

claude-code-live-memory AGENTS.md

A set of working instructions for a codebase that provides a read-only, long-context question-and-answer companion for repositories. The companion runs as a Python server and remembers knowledge separately for each workspace.

In plain words
What is it for?
Use it when working on the live-memory repository, especially for adding dependencies or source files, running its tests, type checks, and deployment-related commands.
Why use it?
It gives coding agents durable rules about the project’s architecture, dependencies, style, and required checks. This reduces guesswork when changing or testing the server.

Instructions file for CodexOpenCode

7 1mo ago A scan 1,254 tokens original Apache-2.0
View the source file shofer-dev/claude-code-live-memory
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/shofer-dev/claude-code-live-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/shofer-dev/claude-code-live-memory

Made for: Codex, OpenCode.

Per session 1,254 This file is loaded in full into every session.
When invoked 1,254 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 $0.01254 $0.01254
Opus 5 $0.00627 $0.00627
Sonnet 5 $0.00251 $0.00251
Haiku 4.5 $0.00125 $0.00125

Measured 2d ago against content hash cb12bb076be7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-live-memory AGENTS.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.

AGENTS.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working agreements — Live Memory

Rules for anyone (human or agent) changing this repo. Keep it short and high-signal — durable rules only, current-state. Full design: DESIGN.md.

What this is

A Claude Code plugin: a persistent, read-only, large-context codebase-Q&A companion. One long-running HTTP MCP server (Python/asyncio) exposes a single tool, ask_live_memory, and accumulates repo knowledge across sessions. State is keyed per workspace (cwd). See DESIGN.md for the full rationale.

Stack & conventions

  • Python ≥ 3.10, asyncio. Server code lives in server/live_memory/; it's a standalone package (server/pyproject.toml). Key deps: mcp (FastMCP, streamable-http), anthropic, starlette, uvicorn, watchdog.
  • Type checking is mypy --strict (pyproject.toml, excludes tests/). No ruff/black/flake8 is configured — don't assume a formatter runs.
  • All tunable magic numbers live in server/live_memory/constants.py — no scattered literals.
  • Add a runtime dep = edit pyproject.toml dependencies + pip install -e .. New source files are auto-discovered (setuptools) — no manual srcs list.

Test / gate

  • ./run-tests.sh (repo root) is the gate: mypy live_memory/ then pytest -q, bootstrapping server/.venv with .[dev] if needed. It's the pre-push hook (git-hooks/pre-push; install once via git-hooks/install.sh). Leave the tree green before committing.
  • Faster inner loop from server/: mypy live_memory/ + pytest -m "not integration" -q. Tests are fully mocked (fake LLM, mocked httpx/OAuth) — no network or API key needed.

Running / deploying the server

  • The server must already be running before Claude Code connects. .mcp.json is type: http — Claude Code connects, never spawns it; if it's down you get a connection error. Dev: cd server && pip install -e . && python -m live_memory → http://127.0.0.1:7711/mcp (+ /health, /stats, /notify, /reload).
  • Prod = a user systemd service on :7711 via deploy/install-service.sh (defaults to a user service — required so zero-config subscription OAuth can read ~/.claude/.credentials.json). It's a supervised singleton serving every session: restart with systemctl --user restart live-memory; never kill it ad hoc — that breaks every connected session (and systemd restarts it anyway).
  • Model/provider: set via env (LIVE_MEMORY_*) or the /live-memory-config command, which writes config.json in the data dir and hot-reloads via POST /reload — no restart. Precedence: env > config.json > defaults.

Read the full file on GitHub · 84 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. 2d ago First seen · 84 lines · 1,254 tokens per session scan A cb12bb076be7

Subscribe to this mod's changes

claude-code-live-memory AGENTS.md is an instructions file published in the GitHub repository shofer-dev/claude-code-live-memory (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,254 tokens to every session, about $0.0063 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.

DevOps and cloudMemory and contextTestingaiclaude-codemcp
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens