recall

recall is a command for coding agents from shimeeuisuk/claude-memory-plugin. It costs 30 tokens per session (634 once invoked), scanned A, original, MIT.

A command that retrieves saved notes about earlier work so an agent can brief you on the current status and continue across computers or days.

In plain words
What is it for?
It helps recover the latest status, next steps, key decisions, and optionally search saved notes for a specific topic.
Why use it?
It removes the need to reread an entire project history when resuming interrupted work.

Command

Part of the claude-memory plugin — 2 skills, 4 commands, 2 hooks shipped together

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/shimeeuisuk/claude-memory-plugin/recall
Clone the repo
git clone --depth 1 https://github.com/shimeeuisuk/claude-memory-plugin

Or install claude-memory, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 2 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.

agentmods badge for recall

README.md
[![agentmods](https://agentmods.dev/badge/commands/shimeeuisuk/claude-memory-plugin/recall.svg)](https://agentmods.dev/commands/shimeeuisuk/claude-memory-plugin/recall)
Your own site
<a href="https://agentmods.dev/commands/shimeeuisuk/claude-memory-plugin/recall"><img src="https://agentmods.dev/badge/commands/shimeeuisuk/claude-memory-plugin/recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 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 $0.00030 $0.00634
Opus 5 $0.00015 $0.00317
Sonnet 5 $0.00006 $0.00127
Haiku 4.5 $0.00003 $0.00063

Measured 3d ago against content hash f39c13fcc6f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recall 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 3d 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.

commands/recall.md · 40 lines

What it actually says

너는 지금 claude-memory 플러그인의 회상(recall) 동작을 수행한다. 기억은 ~/.claude-memory/<project>/ 에서 읽는다.

할 일

  1. 프로젝트 판별: 현재 작업 디렉터리(pwd)의 basename 을 <project> 로 사용.

  2. 다이제스트 먼저 ★ (빠른 재개의 핵심 — 일기 다 읽지 말 것):

    • ~/.claude-memory/<project>/_digest.md 가 있으면 그것부터 읽는다.
    • 거기에 "상태 / 마지막 진행 / 다음 스텝 / 핵심 결정"이 이미 요약돼 있으므로, 보통 이 한 장으로 재개 브리핑이 끝난다.
    • 날짜별 일기 파일은 사용자가 더 깊이 원할 때만 읽는다 (전부 읽지 않는다 → 컨텍스트 절약).
  3. 저장소 없음 처리: ~/.claude-memory/<project>/ 가 없으면

    • 전체 현황(~/.claude-memory/_INDEX.md)이 있으면 보여주며 "다른 프로젝트에서 작업했었나요?" 안내.
    • 없으면 "아직 기억이 없습니다. /claude-memory:remember 로 첫 기억을 남겨보세요." 후 종료.
  4. 키워드 검색 (사용자가 인자 $ARGUMENTS 로 특정 주제를 줬을 때만):

    grep -rli "<키워드>" ~/.claude-memory/<project>/
    
    • 0건이면 동의어/음차로 1회 재시도. 그래도 없으면 무엇을 찾는지 물음.
    • 매칭된 일기 파일을 Read 로 읽는다.
  5. 브리핑 (이 순서로):

    • ① 마지막 상태_digest.md 의 상태 + 다음 스텝 을 그대로 — 재개의 핵심
    • ② 핵심 결정_digest.md 의 carry-forward 결정 (있으면)
    • ③ 더 볼 것 — 드릴다운 선택지 2~4개 (특정 날짜 일기 / 키워드 검색 / 전체 프로젝트 현황(_INDEX.md))

전체 현황 보기

사용자가 "전체 / 모든 프로젝트 / 뭐 하고 있었지" 처럼 물으면 ~/.claude-memory/_INDEX.md 를 읽어 프로젝트별 상태·마지막 갱신을 표로 보여준다.

검색·읽기는 store 폴더로만 한정한다 (코드 repo나 다른 폴더 순회 금지).

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. 3d ago First seen · 40 lines · 30 tokens per session scan A f39c13fcc6f4

Subscribe to this mod's changes

recall is a command published in the GitHub repository shimeeuisuk/claude-memory-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 634 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.