A conversation-archiving workflow that saves finished topics or imported conversations as Markdown records with a checked summary. A memory shelf is a collection of these saved conversation records.

Use it to archive completed topics, save whole conversations, or store research and session notes before the conversation becomes too large.

It reduces context size while preserving decisions, timelines, open questions, and other useful details for later reference.

shelve — Skill for Claude Code by ignatenkofi

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.

Any agent

npx skills add ignatenkofi/memshelf-mcp --skill shelve

Clone the repo

git clone --depth 1 https://github.com/ignatenkofi/memshelf-mcp

Made for: Claude Code.

Or install memshelf, the plugin that ships this one along with the rest of its 1 skill, 3 hooks.

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/skills/ignatenkofi/memshelf-mcp/shelve/github.svg)](https://agentmods.dev/skills/ignatenkofi/memshelf-mcp/shelve)

Your own site

<a href="https://agentmods.dev/skills/ignatenkofi/memshelf-mcp/shelve"><img src="https://agentmods.dev/badge/skills/ignatenkofi/memshelf-mcp/shelve/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/skills/ignatenkofi/memshelf-mcp/shelve"><img src="https://agentmods.dev/badge/skills/ignatenkofi/memshelf-mcp/shelve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,183 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	$0.00079	$0.02183
Opus 5	$0.00039	$0.01092
Sonnet 5	$0.00016	$0.00437
Haiku 4.5	$0.00008	$0.00218

Measured 11d ago against content hash 72b881042c60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

shelve 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 11d 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.

adapters/claude-code/skills/shelve/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/shelve — offload an episode to the memory shelf (M0, prompt-only)

Prefer the tool when it is installed. memshelf shelve --shelf … --slug … --kind … --digest … --section … does everything below in one call — redaction, the digest contract, composition, the episode write and the auto-commit — and cannot drift from the contract the way a prompt can. These steps are the fallback for hosts without memshelf; keep them in sync with core/shelve.py when the contract changes.

Required sections by kind. The contract is enforced before anything is written — by the tool and by the fallback alike — so a missing section costs a failed call, not a broken episode. Digest is always required; on top of it:

kind required besides Digest

topic Decisions

session Timeline, Open threads

research any one non-empty body section

Section names are matched exactly. Known sections render in this order: Decisions → Timeline → Artifacts → Open threads → Raw excerpts; anything else keeps insertion order after them. Source of truth — _REQUIRED_SECTIONS in core/episode.py.

This lives here, not only in step 2, because the tool path skips the body of this skill: you read the pointer above, call memshelf shelve, and meet the contract as an error. That happened on 2026-08-03 with a topic episode written without Decisions.

`kind`	required besides `Digest`
`topic`	`Decisions`
`session`	`Timeline`, `Open threads`
`research`	any one non-empty body section

Prerequisites

MEMSHELF_ROOT env var (or an explicit path given by the user) points to an initialized shelf: a docshelf shelf with categories topics, research, sessions and provider: none.
Shelf write path: docshelf-mcp MCP tools if attached, otherwise the Python library fallback in step 4.
Read the shelf's PII/redaction policy first if POLICY.md exists in the shelf root — it overrides the generic rules below.

Steps

Pick the cut. If the user named a topic, shelve that. Otherwise propose candidates: topics that are closed (conclusion reached, no activity for a while) with a rough token weight each (chars/4), and let the user confirm. Never shelve the currently active topic uninvited.

Read the full file on GitHub · 173 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.

11d ago First seen · 173 lines · 79 tokens per session scan A 72b881042c60

Subscribe to this mod's changes

shelve is a skill published in the GitHub repository ignatenkofi/memshelf-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 2,183 once invoked, about $0.0004 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.

Data and AI Git and workflow Memory and context agent-memory ai-agents claude context-window episodic-memory

syncing-memory-filesystem

Diagnose and repair MemFS repository setup, remote sync, authentication failures, optional backup remotes, or merge/rebase conflicts. Do not load for routine memory reads or edits.

letta-ai/letta-code · 42 tokens

install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…

volcengine/OpenViking · 191 tokens

code-runner

Execute Python code snippets in a sandboxed environment. Supports data analysis, visualization, and quick scripts.

fuyuxiang/echo-agent · 24 tokens

github-ops

GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.

fuyuxiang/echo-agent · 31 tokens

init

Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.

rekal-dev/rekal-cli · 75 tokens

learn

Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.

AgentToolkit/altk-evolve · 40 tokens