memory-processor

A daily-memory processor that reads a day's conversation transcript and turns notable entities, decisions, and ideas into linked knowledge cards. It also creates a daily summary and connects the cards in an Obsidian vault, a folder of linked Markdown notes.

In plain words
What is it for?
Use it to process daily transcripts, preserve important facts and decisions, build links between related notes, and create daily summaries.
Why use it?
It turns raw conversation logs into organized, searchable notes without manually sorting and linking every entry.

Skill for Claude CodeCodex

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/smixs/iva-agent/memory-processor
Any agent
npx skills add smixs/iva-agent --skill memory-processor
Clone the repo
git clone --depth 1 https://github.com/smixs/iva-agent

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,575 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 $0.00106 $0.01575
Opus 5 $0.00053 $0.00788
Sonnet 5 $0.00021 $0.00315
Haiku 4.5 $0.00011 $0.00158

Measured 2d ago against content hash 5e7de3e307b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-processor 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.

scripts/memory/instructions/memory-processor/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memory-processor — daily transcript → cards + summary

Turn one day of raw conversation into durable, navigable memory.

This skill is judgment-first: the model (you) does the classification, tagging, and linking. The autograph Python scripts are used only for mechanical work (enforce schema, repair links, generate MOCs, decay, touch). enrich.py is never used — you are the enrichment.

Inputs

  • daily/YYYY-MM-DD.md — the day's raw two-sided transcript (## HH:MM [text|voice|video|photo|forward from: …] for the user, ## HH:MM [iva] for Iva's replies; older days may use legacy [eva]). See scripts/memory/instructions/rules/daily-format.md.
  • schema.json — the vault schema (types, domains, decay).
  • Existing cards under cards/** and prior summaries under summaries/, weekly|monthly|yearly/ — for linking and dedup.

Outputs

  1. Zero or more entity/decision/idea cards under cards/<kind>/.
  2. One daily-summary card at summaries/daily/YYYY-MM-DD.md.
  3. A processing marker appended to the raw daily file (never edit existing entries).

Layout & types (from schema.json)

What Folder type
Raw transcript (read-only log) daily/YYYY-MM-DD.md — (not a card)
Daily summary summaries/daily/YYYY-MM-DD.md daily-summary
Weekly / monthly / yearly summary weekly/, monthly/, yearly/ *-summary
Knowledge note / thought cards/notes/ note
Person / org cards/contacts/ contact
Project cards/projects/ project
Idea / proposal cards/ideas/ idea
Decision cards/decisions/ decision

Read the full file on GitHub · 118 lines

Files

What ships with it

8 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. 2d ago First seen · 118 lines · 106 tokens per session scan A 5e7de3e307b1

Subscribe to this mod's changes

memory-processor is a skill published in the GitHub repository smixs/iva-agent (189 stars, last pushed 6d ago), licensed MIT. It adds 106 tokens to every session and 1,575 once invoked, about $0.0005 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.