What is prime-memory?

A command for studying the memory pipelines that keep an agent’s stored context current. These include recurring reflection, weekly synthesis, dream consolidation, session cleanup, search, indexing, and working memory.

Use it to inspect the files and architecture behind automated memory updates, searches, indexing, session flushes, and the agent’s ongoing working memory.

It provides a structured way to understand how past interactions are collected, organized, refreshed, and retrieved.

How TheSmokeDev/taskchad-os configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/commands/core_piv_loop/prime-memory.md

Clone the repo

git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/prime-memory/github.svg)](https://agentmods.dev/commands/thesmokedev/taskchad-os/prime-memory)

Your own site

<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/prime-memory"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/prime-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/thesmokedev/taskchad-os/prime-memory"><img src="https://agentmods.dev/badge/commands/thesmokedev/taskchad-os/prime-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 806 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00024	$0.00806
Opus 5.5	$0.00010	$0.00322
Sonnet 5.5	$0.00005	$0.00161
Haiku 4.5	$0.00002	$0.00081

Measured 1mo ago against content hash ebc432d5eaae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prime-memory 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 1mo 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.

.claude/commands/core_piv_loop/prime-memory.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prime: Memory Pipelines Slice

Objective

Build understanding of the 5 automated memory pipelines that keep The Homie's memory current: heartbeat, daily reflection, weekly synthesis, dream consolidation, and session flush. Plus the search/indexing layer, working memory (Living Mind), and episodes (autobiography).

Key Files to Read

Read these files in order. Pipelines live in .claude/scripts/; search and support modules are alongside them.

Architecture doc (read first)

@.claude/sections/03_memory_pipelines.md

Config and shared state

@.claude/scripts/config.py @.claude/scripts/shared.py

Heartbeat (every 30 min)

@.claude/scripts/heartbeat.py

Daily reflection (8 AM)

@.claude/scripts/memory_reflect.py

Weekly synthesis (Sunday 8 PM)

@.claude/scripts/memory_weekly.py

Dream consolidation (post-weekly + standalone)

@.claude/scripts/memory_dream.py

Session flush (on session end / pre-compact)

@.claude/scripts/memory_flush.py

Search and indexing

@.claude/scripts/memory_search.py @.claude/scripts/memory_index.py @.claude/scripts/db.py

Identity payload reader (shared shim)

@.claude/chat/cognition/identity_payload.py

Working memory (Living Mind Phase 1)

@.claude/scripts/living_memory.py

Episodes (Living Mind Act 3)

@.claude/scripts/episodes.py

Entity compilation engine

@.claude/scripts/entity_extractor.py

Slice Boundaries

Owns: heartbeat gather+reason, daily reflection, weekly synthesis, dream consolidation (4 phases), session flush, memory search (keyword/semantic/hybrid), markdown indexing, working memory CRUD, episode write/consolidate, entity extraction+compilation
Does NOT own: recall pipeline (.claude/chat/cognition/recall.py — see /prime-signal), chat routing, runtime provider selection, vault structure (canonical memory lives in vault/memory/)
Cross-slice touchpoints: all pipelines use run_with_fallback() from runtime for LLM calls; reflection/synthesis call entity compilation post-step; dream reads episodes; flush writes episodes; heartbeat writes working-memory observations

Read the full file on GitHub · 88 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.

1mo ago First seen · 88 lines · 24 tokens per session scan A ebc432d5eaae

Subscribe to this mod's changes

prime-memory is a command published in the GitHub repository TheSmokeDev/taskchad-os (28 stars, last pushed 23d ago), licensed MIT. It adds 24 tokens to every session and 806 once invoked, about $0.0001 per session on Opus 5.5. 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.

Memory and context Orchestration agent-memory ai-agents desktop-agent operating-room second-brain

patterns

Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).

mycelium-hq/ai-brain-starter · 20 tokens

perf-difficult-conversation

Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…

frankxai/Starlight-Intelligence-System · 93 tokens

design-regimen

Design an integrated weekly regimen — training, nutrition, sleep, stress, recovery — matched to the person's actual life. Composes with gym-training-expert and health-nutrition-expert for domain detail. Produces a sustainable architecture, not an extreme program. Not medical advice.

frankxai/Starlight-Intelligence-System · 60 tokens

reclaim-knowledge

Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.

frankxai/Starlight-Intelligence-System · 58 tokens

org-role-design

Design or redesign a role with explicit decision rights, measurable accountabilities, success criteria, escalation path, interfaces with adjacent roles, and common failure modes. Refuses RACI-only outputs and vague accountabilities. Output anchors the role for hiring, performance, and succession downstream.