memory-ingest

memory-ingest is a command for coding agents from eddiebelaval/squire. It costs 0 tokens per session (688 once invoked), scanned A, original, MIT.

A command that saves useful facts, decisions, discoveries, and corrections from a conversation into both a memory file and a verbatim store.

In plain words
What is it for?
Use it to file insights about a topic, save a session summary, record a decision, or interactively choose what to preserve.
Why use it?
It prevents important reasoning and project context from disappearing when the conversation ends.

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/eddiebelaval/squire/memory-ingest
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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.

agentmods badge for memory-ingest

README.md
[![agentmods](https://agentmods.dev/badge/commands/eddiebelaval/squire/memory-ingest.svg)](https://agentmods.dev/commands/eddiebelaval/squire/memory-ingest)
Your own site
<a href="https://agentmods.dev/commands/eddiebelaval/squire/memory-ingest"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/memory-ingest.svg" alt="Measured on agentmods" height="20"></a>
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 688 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 $0.00688
Opus 5 $0.00000 $0.00344
Sonnet 5 $0.00000 $0.00138
Haiku 4.5 $0.00000 $0.00069

Measured yesterday against content hash 97dbf4594f99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-ingest 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.

commands/memory-ingest.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/memory-ingest -- File Insights Back Into Memory

You capture valuable analysis, discoveries, or decisions from the current conversation and file them into the MEMORY.md wiki AND MemPalace verbatim store. This is the "query results file back" pattern: good answers shouldn't disappear into chat history.

Arguments: $ARGUMENTS


Route by Arguments

Input Action
"<topic>" File the current conversation's insights about this topic
--session File a session summary (end-of-session compaction)
--decision "<what>" File a specific decision with context and rationale
(empty) Interactive: ask what to file

Process

Step 1: Extract

From the current conversation, extract:

  • Facts learned (new information about projects, people, tools)
  • Decisions made (with rationale and alternatives considered)
  • Discoveries (patterns, connections, insights)
  • Corrections (things we got wrong and fixed)

Step 2: Classify

For each extracted item, determine:

  • Memory type: user | feedback | project | reference
  • Target file: existing memory file to UPDATE, or new file to CREATE
  • Staleness risk: will this be stale in days, weeks, or months?

Step 3: File to MEMORY.md Layer

For each item:

If updating existing file:

  1. Read the target file
  2. Integrate new information (don't duplicate, merge)
  3. Update the frontmatter description if scope changed
  4. Verify MEMORY.md index entry still accurate

If creating new file:

  1. Write file with proper frontmatter (name, description, type)
  2. Follow body structure for type (feedback: rule + Why + How to apply; project: fact + Why + How to apply)
  3. Add entry to MEMORY.md index under correct section
  4. Keep index entry under 150 chars

Step 4: File to MemPalace Layer

For each item, also store the verbatim conversation context in MemPalace:

mempalace add_drawer --wing eddie_memory --room <appropriate_room> --content "<verbatim context>"

Read the full file on GitHub · 93 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. yesterday First seen · 93 lines · 0 tokens per session scan A 97dbf4594f99

Subscribe to this mod's changes

memory-ingest is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 688 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 2026-09-03.

Related

Other commands, from other repositories

remember

Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…

yonatangross/orchestkit · 62 tokens

memory

Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…

yonatangross/orchestkit · 64 tokens

paul:resume

Restore context from handoff and continue work.

ChristopherKahler/paul · 13 tokens

dream

Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index. Use when memory files have accumulated over many sessions and need cleanup. Do NOT use for storing new decisions (use remember) or searching memory (use memory).

yonatangross/orchestkit · 55 tokens

context-health

Dashboard de salud del contexto activo con predicción de degradación y recomendaciones de compactación. Usa cuando el usuario dice "context health", "salud del contexto", "degradation", "compactar contexto", "context overflow", "tokens", "session health", "compact", "contexto lleno". Monitorea degrdación del contexto…

doncheli/don-cheli-sdd · 77 tokens

capturar

Capturar ideas y notas sin interrumpir el flujo de trabajo. Usa cuando el usuario dice "capturar idea", "quick note", "nota rápida", "grab this", "take a note", "guardar idea", "note to self", "capture thought", "I should remember", "guardar esto". Guarda en memoria persistente sin romper el contexto actual.

doncheli/don-cheli-sdd · 74 tokens