memory-init

A command for creating or resetting the files used by a persistent memory system.

In plain words
What is it for?
Use it to initialize memory, reset learned information, or preserve stored patterns while resetting other memory.
Why use it?
It gives you a clean starting point when memory files are missing, outdated, or need to be cleared.

Command

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/dmzoneill/redhat-ai-workflow/memory-init
Clone the repo
git clone --depth 1 https://github.com/dmzoneill/redhat-ai-workflow
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 612 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 $0.00000 $0.00612
Opus 5 $0.00000 $0.00306
Sonnet 5 $0.00000 $0.00122
Haiku 4.5 $0.00000 $0.00061

Measured 2d ago against content hash 9bfd7d290104, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-init 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.

docs/commands/memory-init.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/memory-init

Initialize or reset memory files to a clean state.

Overview

Initialize or reset memory files to a clean state.

Underlying Skill: memory_init

This command is a wrapper that calls the memory_init skill. For detailed process information, see skills/memory_init.md.

Arguments

Argument Required Description
confirm No -

Usage

Examples

skill_run("memory_init", '{"confirm": true}')
skill_run("memory_init", '{"confirm": true, "reset_learned": true}')
skill_run("memory_init", '{"confirm": true, "reset_learned": true, "preserve_patterns": true}')

Process Flow

This command invokes the memory_init skill. The process flow is:

flowchart LR
    START([User runs /memory-init]) --> VALIDATE[Validate Arguments]
    VALIDATE --> CALL[Call memory_init skill]
    CALL --> EXECUTE[Execute Skill Steps]
    EXECUTE --> RESULT[Return Result]
    RESULT --> END([Complete])

    style START fill:#6366f1,stroke:#4f46e5,color:#fff
    style END fill:#10b981,stroke:#059669,color:#fff
    style CALL fill:#3b82f6,stroke:#2563eb,color:#fff
```text

For detailed step-by-step process, see the [memory_init skill documentation](../skills/memory_init.md).

## Details

## Usage

**Reset state files only (preserves learned patterns):**
```text
skill_run("memory_init", '{"confirm": true}')
```text

**Full reset (including learned memory):**
```text
skill_run("memory_init", '{"confirm": true, "reset_learned": true}')
```text

**Full reset but keep patterns:**
```text
skill_run("memory_init", '{"confirm": true, "reset_learned": true, "preserve_patterns": true}')

What Gets Reset

State Files (always reset)

  • state/current_work.yaml - Active issues, open MRs, follow-ups
  • state/environments.yaml - Environment status, ephemeral namespaces

Learned Files (only with reset_learned=true)

  • learned/runbooks.yaml - Operational procedures
  • learned/teammate_preferences.yaml - Review preferences
  • learned/service_quirks.yaml - Service behaviors
  • learned/patterns.yaml - Error patterns (preserved by default)

Read the full file on GitHub · 96 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 · 96 lines · 0 tokens per session scan A 9bfd7d290104

Subscribe to this mod's changes

memory-init is a command published in the GitHub repository dmzoneill/redhat-ai-workflow (5 stars, last pushed 23d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 612 tokens. 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.