agentmods.dev

agentsmd-memory AGENTS.md

Project instructions for agentsmd-memory, a memory tool that returns suggested changes for project guidance files such as AGENTS.md or CLAUDE.md. The coding agent applies those changes itself.

In plain words
What is it for?
Understanding the project’s memory-file resolution rules, integration setup, and known configuration pitfalls. It documents the memory_save and memory_forget tools.
Why use it?
It helps preserve project-specific decisions and lessons between tasks while keeping the changes reviewable. The instructions also explain which memory file to use and how integrations behave.

Instructions file for CodexOpenCode

1 22d ago A scan 358 tokens original MIT
View the source file jryom/agentsmd-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/jryom/agentsmd-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/jryom/agentsmd-memory

Made for: Codex, OpenCode.

Per session 358 This file is loaded in full into every session.
When invoked 358 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 $0.00358 $0.00358
Opus 5 $0.00179 $0.00179
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash d0513e613f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentsmd-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 yesterday.

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 · 19 lines

What it actually says

agentsmd-memory

Zero-dependency MCP server exposing memory_save/memory_forget. Tools never write files; they return merge instructions the agent applies itself. Ships opencode, Claude Code, and Codex integrations, all injecting a per-turn nudge (shared resolveNudge in src/plugin.mjs, overridable via MEMORY_NUDGE).

Resolution

  • File resolution (unset MEMORY_FILE) prefers AGENTS.md, falls back to CLAUDE.md; nearest-up wins, AGENTS.md beats CLAUDE.md at the same level, and AGENTS.md is created when nothing exists. MEMORY_FILE set = single explicit name, no fallback.
  • memoryFileNames() returns the ordered candidate list; memoryFileName() kept as [0] for back-compat. resolveMemoryFile accepts a name or an array.

Gotchas

  • Claude Code auto-discovers hooks/hooks.json; do NOT list it under hooks in .claude-plugin/plugin.json — causes a "Duplicate hooks file" load failure.
  • Codex also auto-discovers hooks/hooks.json; keep the shared hook command as one string. Codex ignores Claude-style separate args in hook handlers.
  • Claude Code and Codex share .mcp.json, which launches unpinned npx -y agentsmd-memory. This intentionally follows npm's latest tag; plugin-root variables are hook-only in Codex and cannot portably locate the bundled MCP source across both clients.
  • marketplace.json rejects a $schema key and wants the description under metadata.description (not top-level).
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. yesterday First seen · 19 lines · 358 tokens per session scan A d0513e613f64

Subscribe to this mod's changes

agentsmd-memory AGENTS.md is an instructions file published in the GitHub repository jryom/agentsmd-memory (1 stars, last pushed 22d ago), licensed MIT. It adds 358 tokens to every session, about $0.0018 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 context
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

vscode buildNext.instructions.md

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

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 · 7,104 tokens

langchain AGENTS.md

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