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 n1nja88888/deardiary --skill journal-memorygit clone --depth 1 https://github.com/n1nja88888/deardiaryWrote 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/n1nja88888/deardiary/journal-memory)<a href="https://agentmods.dev/skills/n1nja88888/deardiary/journal-memory"><img src="https://agentmods.dev/badge/skills/n1nja88888/deardiary/journal-memory/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/n1nja88888/deardiary/journal-memory"><img src="https://agentmods.dev/badge/skills/n1nja88888/deardiary/journal-memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00070 | $0.00644 |
| Opus 5 | $0.00035 | $0.00322 |
| Sonnet 5 | $0.00014 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
journal-memory 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 8d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Journal Memory
The user has connected deardiary: their handwritten diaries (possibly spanning decades), transcribed and distilled, served over MCP. You can know who they are without making them repeat their life story. Use it with care.
When to reach for it
- The conversation turns personal: life decisions, careers, relationships, feelings, plans, regrets.
- The user references their own past ("当年", "我以前", "my ex-boss", a name you don't know).
- The user asks you for advice that depends on who they are.
- The user explicitly asks: "look it up in my journal", "你知道我的".
How to use it well
- Start with
get_profile— one cheap call that answers most background questions (who they are, life chapters, key people, how they changed). Do this before asking the user background questions they've already lived. - Follow the links. The distilled layer is a linked wiki:
[[YYYY-MM-DD]]cites the diary entry a claim came from (fetch withread_entry), and[[Name]]points at another wiki page (fetch withget_page). Follow links to sources instead of re-searching or guessing. - Names, places, themes you don't recognize →
get_page(name)— person pages unify nicknames across the years; place and theme pages trace one thread of life.get_indexmaps every page that exists. - "When did I ..." / vague memories →
search_journal(query), thenread_entry(date)on promising hits for the full faithful text. - Understanding an era ("my Beijing years") →
browse_entries(year=...)orget_timelinefor the arc, then drill into entries. - Transcriptions are faithful: ▢ marks illegible characters,
[?]marks uncertain readings. Don't treat uncertain readings as established fact.
Care, always
- This is the most intimate data a person owns. Quote it only when relevant; never volunteer sensitive details the user didn't bring up; never use it to judge, diagnose, or psychoanalyze uninvited.
- The diaries record what the user felt at the time, not eternal truth. People change — the profile's "转变/Changes" section tracks this. Prefer "in 2013 you wrote..." over "you are...".
- If the user seems uncomfortable with a recall, drop it immediately.
- Everything is read-only. You cannot write to the journal — by design. Humans write; agents read.
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.
- 8d ago First seen · 51 lines · 70 tokens per session scan A 8aee7462540f
journal-memory is a skill published in the GitHub repository n1nja88888/deardiary (0 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 644 once invoked, about $0.0003 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.