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 skills add tigu77/tiguclaw --skill db-maintenancegit 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/skills/tigu77/tiguclaw/db-maintenance)<a href="https://agentmods.dev/skills/tigu77/tiguclaw/db-maintenance"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/db-maintenance/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.
<a href="https://agentmods.dev/skills/tigu77/tiguclaw/db-maintenance"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/db-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02404 |
| Opus 5 | $0.00000 | $0.01202 |
| Sonnet 5 | $0.00000 | $0.00481 |
| Haiku 4.5 | $0.00000 | $0.00240 |
Grade A, and why
db-maintenance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DB 유지보수
<home>/data/tiguclaw.db 한 파일에 기억·세션·대화 기록이 전부 있다. 그래서 이 문서의
순서는 백업 → 용량 → 아카이브다. 크기는 나중에 문제가 되지만 백업은 처음부터 문제다.
0. 먼저 잰다 — 숫자를 여기서 읽지 말고 지금 재라
★이 문서에 "현재 몇 MB · 몇 년 뒤 1GB" 같은 기준선을 적어두지 않는다. 그런 값은 적는 순간부터 늙고, 다음 사람이 그걸 사실로 믿는다(실제로 이 문서가 두 번 틀린 수치를 들고 있었다 — 한 번은 증가율을, 한 번은 그 근거를). 재는 법만 둔다.
DB="<home>/data/tiguclaw.db"
sqlite3 "$DB" "
WITH sz AS (SELECT
(SELECT SUM(pgsize) FROM dbstat WHERE name='transcripts') t,
(SELECT SUM(pgsize) FROM dbstat WHERE name LIKE 'transcripts_fts%') f,
(SELECT page_count*page_size FROM pragma_page_count(), pragma_page_size()) total),
grow AS (SELECT sum(length(content))*1.0 c, (max(ts)-min(ts))/86400000.0 days
FROM transcripts WHERE ts > (strftime('%s','now')-30*86400)*1000)
SELECT
'현재 '||round(total/1048576.0)||'MB (대화 '||round(t/1048576.0)||' + 색인 '||round(f/1048576.0)||' = '||round(100.0*(t+f)/total)||'%)',
'월 증가 ~'||round((c/nullif(days,0))*30*(1.0+f*1.0/nullif(t,0))/1048576.0)||'MB',
'1GB 까지 '||round((1073741824.0-total)/nullif((c/nullif(days,0))*30*(1.0+f*1.0/nullif(t,0)),0)/12.0,1)||'년'
FROM sz, grow;"
★증가는 대화 원문만 세면 틀린다 — 검색 색인이 원문에 비례해 따라 붙는다(그 비율도 위 쿼리가 현재 값으로 잰다). 원문만 세서 증가율을 절반으로 잡은 적이 있다.
판정: transcripts(대화 원문) + transcripts_fts(그 색인)가 대부분이면 정상이다 —
둘 다 설계상 무한 증가고 대화가 쌓이는 만큼 는다. events 는 상한이 있어 안 는다.
1GB 까지 몇 년이 남았는지가 구조를 바꿀 때인지 아닌지의 눈금이고, SQLite 는 수 GB 도
잘 다루므로 수백 MB 에서 손대는 건 이르다.
1. 백업 — 이미 자동으로 돈다
★먼저 이것부터 알아라: 백업은 v0.27.0 부터 자동이다. 스케줄이 아니라 데몬 유지보수
루프(코어 자기보전 루프(core/self-maintenance) → store/backup.ts)에서 하루 한 벌씩 VACUUM INTO 로 뜨고 7벌만
남긴다. 스케줄 목록에는 안 보인다 — 없다고 "백업 체계가 없다"고 결론내지 마라(실제로
그렇게 오판한 적이 있다. 그리고 중복 스케줄을 제안할 뻔했다).
상태 확인은 두 가지로:
/status → "백업: 3시간 전 · 7벌 (940MB)" 한 줄
ls -lt <home>/data/backup/ → 실제 파일
성공은 일부러 조용하다(매일 알림은 배경 소음이 된다). 실패와 첫 벌만 알린다.
끄려면 settings.json 의 backup.enabled: false — 기본은 켜짐이다.
손으로 한 벌 더 뜨려면:
mkdir -p "<home>/data/backup"
sqlite3 "$DB" "VACUUM INTO '<home>/data/backup/tiguclaw-$(date +%F).db'"
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.
- 4d ago Changed · +1 lines d5a6105f9794
- 9d ago First seen · 120 lines · 0 tokens per session scan A 7b753467f1e8
db-maintenance is a skill published in the GitHub repository tigu77/tiguclaw (6 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,404 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 2026-08-31.
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…
api-reference
Memoria REST API endpoints, request/response formats, auth, rate limits. Use when calling or implementing API endpoints.
architecture
Memoria codebase structure, workspace layout, key traits, database tables, config patterns, and testing conventions. Use when navigating or modifying Memoria code.
deployment
Deploy Memoria with Docker Compose or Kubernetes. Environment variables, multi-instance setup, security. Use when deploying or configuring Memoria.
setup
Install Memoria and configure MCP for AI tools (Kiro, Cursor, Claude Code, Codex, Gemini CLI). Decision tree for Cloud vs self-hosted mode, database, embedding provider. Use when helping users set up Memoria.
plugin-development
Create, test, sign, and publish Memoria governance plugins. Covers Rhai and gRPC runtimes, manifest format, lifecycle. Use when developing or managing plugins.