A command for examining and improving AI prompts, skills, commands, and settings so they can use a persistent memory system. Persistent memory means saved information that remains available across sessions.

Use it to audit or enhance CLAUDE.md files, system prompts, skills, commands, hooks, and MCP tool usage, or create a memory-aware skill.

It helps connect existing AI instructions and tools to stored project knowledge instead of leaving them unaware of relevant past context.

integrate — Command by zircote

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 commands/zircote/subcog/integrate

Clone the repo

git clone --depth 1 https://github.com/zircote/subcog

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,536 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.03536
Opus 5	$0.00006	$0.01768
Sonnet 5	$0.00002	$0.00707
Haiku 4.5	$0.00001	$0.00354

Measured 2d ago against content hash 928781b33253, 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 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.

commands/integrate.md · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/subcog:integrate

Analyze, enhance, or create AI prompts, skills, commands, and configurations to leverage Subcog's persistent memory system effectively.

Usage

/subcog:integrate                           # Interactive mode (recommended)
/subcog:integrate --analyze                 # Analyze current project for integration opportunities
/subcog:integrate --enhance CLAUDE.md       # Enhance specific file
/subcog:integrate --create skill            # Create new memory-aware artifact

Interactive Workflow

Step 1: Discover Current State

Check for existing Subcog integration:
- Read project CLAUDE.md if exists
- Read ~/.claude/CLAUDE.md if exists
- Check for hooks/hooks.json or .claude/hooks.json
- Scan skills/ and commands/ directories
Call subcog_status to verify memory system is healthy
Call subcog_recall with query "subcog integration patterns" to surface existing guidance

Step 2: Ask What to Analyze/Enhance

Use AskUserQuestion to present options:

CLAUDE.md / System Prompts
Skills & Commands
Hooks Configuration
MCP Tool Usage Patterns
All of the above (comprehensive audit)

Step 3: Perform Analysis

Based on selection, analyze artifacts and generate recommendations.

Step 4: Present Recommendations

Show a structured report with:

Current state summary
Missing integration points
Specific recommendations with code snippets
Priority ranking (high/medium/low impact)

Step 5: Offer to Apply Changes

Ask user which recommendations to apply, then make the changes.

Analysis Patterns

Check for:

Subcog Memory Protocol section exists
subcog_init call instruction at session start
Recall-before-implement pattern documented
Capture-immediately guidance present
MCP-only access pattern specified (no shell commands)
Namespace guidance for the project domain

Read the full file on GitHub · 475 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.

2d ago First seen · 475 lines · 12 tokens per session scan A 928781b33253

Subscribe to this mod's changes

integrate is a command published in the GitHub repository zircote/subcog (28 stars, last pushed 29d ago), licensed MIT. It adds 12 tokens to every session and 3,536 once invoked, about $0.0001 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.

Data and AI Memory and context Research ai ai-assistant cli developer-tools embeddings hybrid-search

integrate

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/subcog:integrate

Usage

Interactive Workflow

Step 1: Discover Current State

Step 2: Ask What to Analyze/Enhance

Step 3: Perform Analysis

Step 4: Present Recommendations

Step 5: Offer to Apply Changes

Analysis Patterns

What this file has done since we first saw it

Other commands, from other repositories

setup

version

index

analyst

codesage-reindex

advanced-code-review-context