memory-tidy

memory-tidy is a skill for Claude Code, Codex from tigu77/tiguclaw. It costs 0 tokens per session (2,817 once invoked), scanned A, original, Apache-2.0.

A memory-maintenance skill for finding duplicate, expired, or overly long entries in an assistant's memory index. It suggests changes for a person to approve and archives entries instead of permanently deleting them.

In plain words
What is it for?
Use it to measure memory usage, review duplicate or outdated entries, compress descriptions, and prepare safe merge or archive suggestions.
Why use it?
Large memory indexes can consume context and repeat the same information. The skill helps reduce clutter while keeping archived entries searchable and recoverable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to measure memory usage, review duplicate or outdated entries, compress descriptions, and prepare safe merge or archive suggestions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tigu77/tiguclaw/memory-tidy
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 tigu77/tiguclaw --skill memory-tidy
Clone the repo
git clone --depth 1 https://github.com/tigu77/tiguclaw

Made for: Claude Code, Codex.

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-tidy

README.md
[![agentmods](https://agentmods.dev/badge/skills/tigu77/tiguclaw/memory-tidy/github.svg)](https://agentmods.dev/skills/tigu77/tiguclaw/memory-tidy)
Your own site
<a href="https://agentmods.dev/skills/tigu77/tiguclaw/memory-tidy"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/memory-tidy/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.

agentmods 80×15 button for memory-tidy

Your own site · 80×15
<a href="https://agentmods.dev/skills/tigu77/tiguclaw/memory-tidy"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/memory-tidy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,817 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.02817
Opus 5 $0.00000 $0.01409
Sonnet 5 $0.00000 $0.00563
Haiku 4.5 $0.00000 $0.00282

Measured 2d ago against content hash 86e5371d2ccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

memory-tidy 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.

skills/memory-tidy/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

메모리 정리

0. 왜 필요한가

상시 규범은 계속 늘어난다 — 사용자가 계속 입력하고, 비서도 관측을 적는다. 오래 쓴 설치에서는 메모리 인덱스가 매 턴 실리는 상수 중 가장 큰 조각이 되고 캡에 닿는다 (개발 인스턴스 실측: 3주에 약 4배). ★네 설치의 값은 /status 와 아래 §1 로 직접 재라 — 이 숫자를 그대로 옮겨 적지 마라.

캡을 내리는 건 답이 아니다. 같은 날 재보니 캡을 반으로 내리면 사람이 쓴 77건이 잘리고 그 안에 상시 행동 규칙이 있었다(style-never-auto-push-… 등). 경계도 촘촘했다 — 잘리는 것 최대 access 19 / 남는 것 최소 20.

진짜 여유는 중복에 있다. 같은 실측에서 나온 것:

  • 「답글 형식」이 3건(access 287·278·257 — 상위 3개가 전부 한 주제다)
  • 「스킬화」 3건 · 「위임」 3건 · 「위키 커밋·푸시」 2건(거의 같은 문장) · 「system-reminder」 2건
  • 자동 생성 feedback_growth_* 24건 5.1KB(15%) — 기계 해시 이름
  • 만료된 것 — 지나간 일정·끝난 작업처럼 시효가 있는 사실이 아직 매 턴 실린다

1. 하드룰 (여기부터 읽어라)

  • 지우지 않는다. archive_memory 를 쓴다 — 인덱스에서만 내리고 검색으로는 계속 찾히며(FTS 는 아카이브 무관) 되돌릴 수 있다(restore:true). delete_memory 는 이 스킬에서 쓰지 마라.
  • 한 판은 한 호출이다. archive_memorynames 배열을 받는다 — 승인받은 묶음을 한 번에 넘겨라(건별로 20번 부르지 마라: 왕복도 승인도 스무 배고, 중간에 턴이 끊기면 «절반만 정리된» 상태가 남는다).
  • 자동으로 합치지 않는다. 「이건 중복이다」가 틀리면 규칙이 조용히 사라지고, 다음 사고 때야 알게 된다. 제안까지가 이 스킬의 일이고, 고르는 건 사람이다.
  • 재고 나서 말한다. "많다"·"중복이다"는 숫자를 대고 하는 말이다(§2 가 그 숫자다).
  • ★★내린 것은 스스로 돌아오지 않는다 (2026-09-06 실행으로 확인, 정태님 지적). 여기엔 "사실형은 잘려도 자가 회복된다 — retrieveContext → searchMemories → bumpAccess 로 access 가 올라 인덱스로 돌아온다(실측 확인)" 고 적혀 있었는데 코드에 그 경로가 없다. bumpAccess 호출처는 getMemory 하나뿐이고, 검색은 touchSeen(=last_accessed 만) 을 부른다. 게다가 인덱스 정렬은 access_count DESClast_accessed 는 순서에 영향도 없다. 실측: 아카이브한 뒤 검색으로 5번 도달해도 인덱스로 안 돌아왔다(찾히기는 한다). ★그래서 아카이브는 되돌리려면 사람이 archive_memory(restore:true) 를 불러야 한다. 이 문장이 틀린 채로 있으면 «사실형은 내려도 안전하다» 는 근거가 거짓이 되고, 정리할 때마다 사실이 조용히 사라진다.
  • 그래도 규범과 사실은 다르게 다룬다 — 규범은 애초에 여기 있으면 안 된다(add_memory 도구 설명: "여기는 «사실» 자리다 … 「항상 존댓말」·「자동 푸시 금지」는 <home>/AGENT.md"). §4 가 그걸 가려 승격시킨다. 남아 있는 규범은 병합하되 내리지 마라 — 「자동 푸시 금지」는 push 얘기가 나와야 살아나는데 그때는 이미 늦다.

2. 먼저 잰다

list_memories 도구를 쓴다. 이름·종류·설명·읽힌 횟수·인덱스 바이트 + 총량·캡을 한 번에 준다(읽기 전용, 본문 제외).

셸로 DB 를 직접 읽지 마라. 승인 게이트에 걸려 여기서 멈춘다 — 이 스킬의 첫 판이 실제로 그렇게 멈췄고(2026-09-02), 그래서 이 도구가 생겼다. 그리고 DB 를 직접 세면 SQLite length()문자 수라 한국어에서 3배 틀린다(같은 날 내가 그 착시로 «포맷이 1.70배» 라고 잘못 보고했다). 도구는 바이트로 준다.

Read the full file on GitHub · 136 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. 2d ago Changed · +14 lines 86e5371d2ccd
  2. 3d ago Changed · +1 lines 889e25311344
  3. 4d ago First seen · 121 lines · 0 tokens per session scan A 7c4c1a8027bf

Subscribe to this mod's changes

memory-tidy is a skill published in the GitHub repository tigu77/tiguclaw (6 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,817 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 2026-09-04.

Related

Other skills, from other repositories

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

memory-processor

Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…

smixs/iva-agent · 106 tokens

dbrain-processor

Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

smixs/agent-second-brain · 60 tokens

autograph

Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…

smixs/agent-second-brain · 89 tokens

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when asked to check, audit, update, improve, or fix CLAUDE.md files, or when someone mentions project memory optimization.

bearlike/Assistant · 46 tokens

remember

Curates the current conversation into ByteRover's context tree for future retrieval. Use after important decisions, project discussions, or technical deep-dives.

ahkedia/lyra-ai · 32 tokens