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 jegly/Box --skill mood-trackergit clone --depth 1 https://github.com/jegly/BoxWrote 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/jegly/box/mood-tracker)<a href="https://agentmods.dev/skills/jegly/box/mood-tracker"><img src="https://agentmods.dev/badge/skills/jegly/box/mood-tracker.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 5.1 | $0.00040 | $0.01361 |
| Opus 5 | $0.00020 | $0.00681 |
| Sonnet 5 | $0.00008 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
mood-tracker 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 7d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 124 lines · 40 tokens per session scan A b12072f83214
mood-tracker is a skill published in the GitHub repository jegly/Box (802 stars, last pushed 3d ago), with no licence file. It adds 40 tokens to every session and 1,361 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 2026-08-30.
Other skills, from other repositories
automations
Manage Local Studio automations — scheduled prompts the app re-runs on its own — when the user asks to schedule, pause, resume, edit, inspect or delete recurring work, or asks what a scheduled job has been doing.
obsidian
The user's Obsidian vault — searching, reading, creating and appending to their markdown notes, with wikilinks, frontmatter and tags handled the way Obsidian means them. Load when the user mentions their notes, their vault, Obsidian, a daily note, a note by name, or asks you to write something down for them.
chrome
The user's own Chrome — their real window, profile, logins and tabs, driven through the browser extension relay. Load when a task needs a signed-in session, a page they already have open, or anything the headless sandbox browser cannot see.
cua
Computer use — a headless sandbox browser for opening, reading, and interacting with public web pages. Load when the user asks to browse, search, open a page, inspect a link, or when live web content matters and no sign-in is involved.
github
GitHub through the gh CLI that is already installed and signed in on this machine — issues, pull requests, diffs, reviews, Actions runs, code search, and the REST API. Load when the user asks about a repo, an issue, a PR, a review, red CI, or anything on github.com.
subagents
Delegate self-contained work to parallel subagent sessions — when a task splits into independent chunks (research several areas at once, review many files, try approaches in parallel), or when the user asks to fan out, parallelize, or run something in the background.