memory-writer

memory-writer is an agent for Claude Code from cdeust/zetetic-team-subagents. It costs 46 tokens per session (981 once invoked), scanned A, original, MIT.

A helper agent that saves important facts from an agent session into a checkpoint file and a memory store. It is used during context warnings and does not create facts that were not provided.

In plain words
What is it for?
Use it to preserve session summaries, durable project facts, and checkpoints for later work.
Why use it?
It prevents useful session information from being lost when the conversation becomes too long or needs to be resumed. It also keeps the saved record grounded in the available content.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Part of the zetetic-team-subagents plugin — 15 skills, 1 command, 23 agents, 6 hooks, 1 MCP server shipped together

Good fit Use it to preserve session summaries, durable project facts, and checkpoints for…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cdeust/zetetic-team-subagents/memory-writer
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.

Clone the repo
git clone --depth 1 https://github.com/cdeust/zetetic-team-subagents

Made for: Claude Code.

Or install zetetic-team-subagents, the plugin that ships this one along with the rest of its 15 skills, 1 command, 23 agents, 6 hooks, 1 MCP server.

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/memory-writer.svg)](https://agentmods.dev/agents/cdeust/zetetic-team-subagents/memory-writer)
Your own site
<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/memory-writer"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/memory-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 981 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00981
Opus 5 $0.00023 $0.00491
Sonnet 5 $0.00009 $0.00196
Haiku 4.5 $0.00005 $0.00098

Measured 6d ago against content hash 8203c4f41d7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

memory-writer 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 6d 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.

agents/memory-writer.md · 50 lines

What it actually says

Before returning any prose a human will read (paper section, lesson, review report, checkpoint summary, copy recommendation), run the eval from skills/writing/redaction.md on your own output and fix failures in place: no invented facts; zero em dashes, antithesis constructions, or triads in copy; every attribution names its source (unsourced attribution is a coding-standards §8 violation — name it or cut it); cutting proportional to actual slop; ends on a concrete point, not a recap or kicker. The vendored inventory in that skill is authoritative; this gate is its enforcement point (issue #43).

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. 6d ago First seen · 50 lines · 46 tokens per session scan A 8203c4f41d7c

Subscribe to this mod's changes

memory-writer is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 981 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

memory-extractor

OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…

Lifecycle-Innovations-Limited/claude-ops · 21 tokens

evolve-memo

Lightweight PASS-cycle memo agent (v8.57.0+, Layer P). Fires on PASS verdicts after ship to capture observations Scout/Triage saw but did NOT commit to topn. Single-pass, $0.10–0.20 per cycle. Emits carryover-todos.json and memo.md — does NOT do retrospective/digest work (that's the FAIL/WARN retrospective agent's…

mickeyyaya/evolve-loop · 86 tokens

source-ingester

Специализированный агент по ингесту внешних источников (статья, книга, видео, доклад, транскрипт, конспект лекции, экспорт цитат) в персональную базу знаний Obsidian. Делегируй сюда, когда пользователь хочет «обработать статью», «положить книгу в базу», «выжать знания из видео», «обработай конспект лекции», «разбери…

jtprogru/bear-skills · 181 tokens

backlink-manager

Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.

Oshayr/LLM-Wiki · 25 tokens

brain-keeper

Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.

agencia-conversion/agentic-seo-skills · 29 tokens

wiki-auditor

Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file.

Oshayr/LLM-Wiki · 34 tokens