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 DanialDaeHyunNam/omniscitus --skill wrap-upgit clone --depth 1 https://github.com/DanialDaeHyunNam/omniscitusWrote 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/danialdaehyunnam/omniscitus/wrap-up)<a href="https://agentmods.dev/skills/danialdaehyunnam/omniscitus/wrap-up"><img src="https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/wrap-up/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/danialdaehyunnam/omniscitus/wrap-up"><img src="https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/wrap-up.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 | $0.00054 | $0.02884 |
| Opus 5 | $0.00027 | $0.01442 |
| Sonnet 5 | $0.00011 | $0.00577 |
| Haiku 4.5 | $0.00005 | $0.00288 |
Grade A, and why
wrap-up 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 12d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap-up — Topic-Based Session History
Record the current session's work into .omniscitus/history/ as topic-based units.
When to Use
- User types
/wrap-up - User says "마무리", "정리해줘", "wrap up", "session end"
Instructions
Step 1: Initialize
Check if .omniscitus/ exists in the project root. If not, create:
mkdir -p .omniscitus/history
And create .omniscitus/history/_index.yaml with:
units: []
Step 1.5: Weekly Summary Backfill (automatic)
Before analyzing the current session, check whether the last completed ISO week has a weekly summary on disk. If not, generate it first, then proceed with the current session's wrap-up. This runs silently most weeks (summary already present) and only triggers the first wrap-up of a new week.
Rules
- Only generate for completed weeks. A week is complete if its Sunday (ISO Sunday = day 7) is before today. If today is mid-week, skip — there's nothing to summarize yet.
- Store summaries at
.omniscitus/history/_weekly/{YYYY}-W{NN}.mdusing ISO week numbering (2026-W14= Mar 30–Apr 5, 2026). - Track them in
_index.yamlunder a top-levelweekly_summaries:list so birdview can render them without re-walking the filesystem. - If
_weekly/does not exist yet, create it:mkdir -p .omniscitus/history/_weekly.
Procedure
- Compute the current ISO week: today →
{YYYY}-W{NN}. - Compute the previous completed week: subtract 7 days from today, then take its ISO week. Skip generation if that week is the same as the current week (meaning today is still inside it).
- Check
_weekly/{YYYY}-W{NN}.md. If it exists, skip. - Walk
_index.yamlfor all units wherelast_updatedfalls in the previous week's date range. Collect:- total units touched, new vs. appended
- domains touched (with count per domain)
- top decisions / constraints from each unit's
## Context - pending items still open at week end
- Generate the summary file (use language from project convention — Korean if other history units are Korean, otherwise English):
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.
- 12d ago First seen · 330 lines · 54 tokens per session scan A 8a808bf46a9b
wrap-up is a skill published in the GitHub repository DanialDaeHyunNam/omniscitus (5 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 2,884 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.