integrate

An integration guide for adding mnemonic memory operations to existing Claude Code plugins. It uses written workflow instructions and event-driven hooks, which are automated reactions to events.

In plain words
What is it for?
Use it to add memory recall and capture to an existing plugin, configure capture suggestions, or migrate an older mnemonic integration. It is not intended for building a new plugin.
Why use it?
It removes the need to add memory instructions and event handling manually across each plugin component. This lets plugins recall past decisions and capture new learnings across sessions.

Skill for Claude CodeCodex

Part of the mnemonic plugin — 10 skills, 14 commands, 4 agents, 1 hook, 1 plugin shipped together

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 skills/modeled-information-format/mnemonic/integrate
Any agent
npx skills add modeled-information-format/mnemonic --skill integrate
Clone the repo
git clone --depth 1 https://github.com/modeled-information-format/mnemonic

Made for: Claude Code, Codex.

Or install mnemonic, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 4 agents, 1 hook, 1 plugin.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,843 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00083 $0.04843
Opus 5 $0.00042 $0.02422
Sonnet 5 $0.00017 $0.00969
Haiku 4.5 $0.00008 $0.00484

Measured 3d ago against content hash 4fd486ae6105, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integrate 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.

The scan reads SKILL.md. This mod also ships 5 executable files (lib/__init__.py, lib/frontmatter_updater.py, lib/integrator.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/integrate/SKILL.md · 705 lines

How it starts

The opening of the file, as written. The whole thing — 705 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate Skill

Wire mnemonic memory operations into other Claude Code plugins.

When to Use

Use this skill when you want to:

  • Add memory to an existing plugin - Make any plugin mnemonic-aware
  • Enable cross-session learning - Let plugins recall past decisions and learnings
  • Automate capture triggers - Set up hooks that suggest memory capture at the right time
  • Migrate legacy integrations - Convert old marker-less integrations to the new format

Don't use this skill if:

  • You're building a new plugin from scratch (use the core skill directly)
  • You only need to search/capture memories (use /mnemonic:search and /mnemonic:capture)

Overview

This skill enables integrating mnemonic memory capture and recall into other Claude Code plugins. Integration happens through two mechanisms:

  1. Markdown Workflow Edits - Add explicit workflow steps to command/skill/agent markdown files
  2. Event-Driven Hooks - Add hooks that detect events and inject memory context

Both mechanisms work together: Markdown provides explicit workflow guidance, hooks provide automatic event detection.

Quick Start

# Integrate a plugin (adds mnemonic protocol to all components)
/mnemonic:integrate {plugin_path}

# Preview changes without applying
/mnemonic:integrate {plugin_path} --dry-run

# Remove integration
/mnemonic:integrate {plugin_path} --remove

# Rollback last integration (git required)
/mnemonic:integrate {plugin_path} --rollback

For detailed options, see "How to Use This Skill" below.


[CRITICAL] PROTOCOL CONTENT MUST BE VERBATIM

For the mnemonic protocol section (## Memory), you MUST:

  1. Read templates/mnemonic-protocol.md - this is the single source of truth
  2. Insert its content EXACTLY as-is, including sentinel markers
  3. Never abbreviate, modify, or "improve" the protocol text

Exception: Event-driven hooks (Pattern D) are optional and use the provided template code.


Sentinel Markers

Read the full file on GitHub · 705 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 705 lines · 83 tokens per session scan A 4fd486ae6105

Subscribe to this mod's changes

integrate is a skill published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 4,843 once invoked, about $0.0004 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.