Borrowing it
Nothing to install: this file belongs to ThoBustos/openyoko. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ThoBustos/openyoko/main/.claude/skills/unload/SKILL.mdgit clone --depth 1 https://github.com/ThoBustos/openyokoWrote 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/thobustos/openyoko/unload)<a href="https://agentmods.dev/skills/thobustos/openyoko/unload"><img src="https://agentmods.dev/badge/skills/thobustos/openyoko/unload/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/thobustos/openyoko/unload"><img src="https://agentmods.dev/badge/skills/thobustos/openyoko/unload.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 | $0.02568 |
| Opus 5.5 | $0.00000 | $0.01027 |
| Sonnet 5.5 | $0.00000 | $0.00514 |
| Haiku 4.5 | $0.00000 | $0.00257 |
Grade A, and why
unload 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 2mo 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/unload Skill
End-of-day brain dump with intelligent state synthesis. Clear your mind, see your week's reality, and prepare tomorrow.
Usage
/unload
When to use:
- End of day when brain is full
- Before bed to clear mental load
- When feeling overwhelmed with open loops
Key difference from /daily:
/daily= structured morning/evening Q&A ritual with calendar, pillar tracking/unload= pure mind-clearing dump + intelligent state synthesis + tomorrow prep
Prerequisites
Before running this skill, check:
-
Current week journal exists - Look for
{{vault}}/02_JOURNAL/Weekly/{{YYYY}}-W{{WW}}.md- IF MISSING: "You don't have a week journal yet. Would you like to run /weekly first to set up your week?"
-
GLOBAL_STATE.md exists - Check
{{vault}}/00_SYSTEM/GLOBAL_STATE.md- IF MISSING: "No vault found. Run /onboarding first."
Flow
Phase 1: Context Gathering (Silent)
Read these files without outputting anything:
System Core:
{{vault}}/00_SYSTEM/GLOBAL_STATE.md- Current focus, energy, active projects{{vault}}/00_SYSTEM/TODO.md- All tasks, check staleness{{vault}}/00_SYSTEM/IMPORTANT_DATES.md- Anything for tomorrow
Journal:
4. {{vault}}/02_JOURNAL/Weekly/{{YYYY}}-W{{WW}}.md - Current week journal
- Extract: Top 3s (Personal + Professional), Keystone, Pillar Commitments
- Extract: All daily entries so far (Week Progress section)
- Extract: Running Thread items
Projects:
5. All active project _STATE.md files from GLOBAL_STATE's active_projects list
- Note staleness (>7 days = stale)
Activity:
6. {{vault}}/00_SYSTEM/OPS/activity-logs/{{YYYY}}-W{{WW}}.md - What was logged today
Goals:
7. {{vault}}/01_GOALS/{{YYYY}}.md - Year goals for context
8. {{vault}}/02_JOURNAL/Monthly/{{YYYY}}-{{MM}}.md - Month plan (if exists)
Calculate:
- Days since each project _STATE last updated
- Task completion status for Top 3s
- Pillar commitment progress (how many days hit)
- Any waiting/blocked items older than 7 days
- Tomorrow's calendar events (via MCP if available)
- Tomorrow's important dates
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.
- 2mo ago First seen · 346 lines · 0 tokens per session scan A 09e0da18d6d1
unload is a skill published in the GitHub repository ThoBustos/openyoko (9 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,568 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.
unload compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unloadThoBustos/openyoko | Skill | 9 | 2mo ago | MIT | A | 0 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |