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.
npx agentmods add commands/tigu77/tiguclaw/memory-tidygit clone --depth 1 https://github.com/tigu77/tiguclawWrote 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.
[](https://agentmods.dev/commands/tigu77/tiguclaw/memory-tidy)<a href="https://agentmods.dev/commands/tigu77/tiguclaw/memory-tidy"><img src="https://agentmods.dev/badge/commands/tigu77/tiguclaw/memory-tidy.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00034 | $0.00590 |
| Opus 5 | $0.00017 | $0.00295 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
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 yesterday.
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.
What it actually says
memory-tidy 스킬을 그대로 따라 메모리 인덱스를 정리하라.
범위: $ARGUMENTS
지켜야 할 것(스킬 §1 하드룰과 같다 — 여기 다시 적는 이유는 이 매크로만 읽고 시작할 수 있어야 하기 때문이다):
- 지우지 마라.
archive_memory를 쓴다(인덱스에서만 내려가고 검색으로는 계속 찾히며 되돌릴 수 있다).delete_memory는 이 작업에서 쓰지 않는다. - 자동으로 합치지 마라. 「이건 중복이다」가 틀리면 규칙이 조용히 사라진다 — 제안까지가 네 일이고 고르는 것은 사용자다.
- 재고 나서 말하라. "많다"·"중복이다"는 바이트와 건수를 대고 하는 말이다.
- 상시 규범과 사실을 다르게 다뤄라. 사실형(취미·기기·일정)은 잘려도 자가 회복된다 (관련 대화 → 검색 → access 상승 → 인덱스 복귀). 상시 규범은 회복이 안 된다 — 「자동 푸시 금지」는 push 얘기가 나와야 살아나는데 그때는 이미 늦다. 규범은 합치되 내리지 마라.
- 자동 생성분(
feedback_growth_*)은 손대지 마라 — self-growth 소유다. 개수·바이트만 보고.
★한 번에 하는 일을 바운드하라 — 전수로 훑지 마라. list_memories 로 재고 인덱스
바이트 상위 25건까지만 본다. 본문은 최종 후보 몇 건에만 읽는다(첫 판이 197건 본문을
읽다가 16분 넘게 돌았다). 반복 실행이 전제다 — 이번에 앞줄을 줄이면 다음엔 그다음 줄이다.
보고는 이 순서로: ①현재 크기(바이트·건수) ②부류별 후보(중복/만료/과거관측, 각 크기) ③병합안(합칠 것 · 남길 이름 · 합친 한 줄 · 잃는 문장 없음을 확인) ④승인 요청.
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.
- yesterday First seen · 30 lines · 34 tokens per session scan A 1f7d19876d11
memory-tidy is a command published in the GitHub repository tigu77/tiguclaw (6 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 590 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 2026-09-04.
Other commands, from other repositories
revise-claude-md
Update CLAUDE.md with learnings from this session.
instinct-status
Show learned instincts (project + global) with confidence.
instinct-import
Import instincts from external sources.
learn
Extract patterns and learnings from current session.
mempalace-init
Set up MemPalace — install the package, initialize a palace, register the MCP server with Cursor, and verify everything works.
mempalace-status
Show the current state of your memory palace — wings, rooms, drawer counts, and suggestions.