agentmods.dev

mcp-light-memory AGENTS.md

A set of AGENTS.md instructions for a repository that uses MCP Light Memory, a system for storing and retrieving persistent information for coding agents. It defines required memory, checkpoint, recovery, and guard steps.

In plain words
What is it for?
Use it when working in the mcp-light-memory repository, especially for tasks requiring persistent memory, recovery checks, checkpoints, or final guards.
Why use it?
It tells the agent how to preserve operational context across substantial tasks and how to check repository state before finishing.

Instructions file for CodexOpenCode

0 6d ago A scan 248 tokens original MIT
View the source file PeterPirog/mcp-light-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/peterpirog/mcp-light-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/PeterPirog/mcp-light-memory

Made for: Codex, OpenCode.

Per session 248 This file is loaded in full into every session.
When invoked 248 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 $0.00248 $0.00248
Opus 5 $0.00124 $0.00124
Sonnet 5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured 2d ago against content hash dbc98d444367, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-light-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 · 22 lines

What it actually says

Agent Operating Contract

Persistent agent memory: MCP Light Memory (INTERNAL_RAG)

This repository uses INTERNAL_RAG/ as mandatory persistent operational memory.

For every substantial task:

  1. Load the internal-rag skill.
  2. Run mlm.py context --task "<current task>" before the first code modification.
  3. If context reports RECOVERY REQUIRED, inspect Git state, reconstruct work, checkpoint it, and obtain GUARD OK before new edits.
  4. Checkpoint before the first edit, after meaningful milestones, after blockers/failures, before risky long operations, before compaction, and before final response.
  5. Run mlm.py guard before finishing a substantial task.
  6. Do not preload the entire INTERNAL_RAG/ directory.
  7. Verify consequential memory claims against current code/tests/configuration.
  8. Do not store secrets, credentials, production data, or verbose reasoning traces in memory.

Authority order: current user instructions > current code/tests/config > accepted specifications/ADR > verified memory > session notes > hypotheses.

Memory is evidence, not authority. It can be stale.

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 · 22 lines · 248 tokens per session scan A dbc98d444367

Subscribe to this mod's changes

mcp-light-memory AGENTS.md is an instructions file published in the GitHub repository PeterPirog/mcp-light-memory (0 stars, last pushed 6d ago), licensed MIT. It adds 248 tokens to every session, about $0.0012 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.

Memory and contextagent-memorycoding-agentsdeveloper-toolslocal-firstmcpmodel-context-protocol
Related

Other instructions, from other repositories

Agent-Memory-Bridge AGENTS.md

Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.

zzhang82/Agent-Memory-Bridge · 1,089 tokens

mnemic CLAUDE.md

Claude Code instructions for dongtang3/mnemic: This project includes a project-level .mcp.json for the Mnemic memory MCP server.

dongtang3/mnemic · 95 tokens

mnemic AGENTS.md

AGENTS.md instructions for dongtang3/mnemic: Mnemic is a graph-backed long-term memory substrate for coding agents and LLM applications.

dongtang3/mnemic · 221 tokens

repoprimer AGENTS.md

AGENTS.md instructions for repoprimer/repoprimer, a project described as: Local-first, read-only project context for coding agents via MCP.

repoprimer/repoprimer · 237 tokens

plur CLAUDE.md

Instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.

plur-ai/plur · 4,509 tokens

engraphis AGENTS.md

Instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, 0. read this first — two architectures live in one package, 1. commands, ── unified dashboard + memory inspector ── and 2. the v2 recall pipeline (where the real work is).

Coding-Dev-Tools/engraphis · 4,851 tokens