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 jezweb/vite-flare-starter --skill score-importancegit clone --depth 1 https://github.com/jezweb/vite-flare-starterWrote 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/jezweb/vite-flare-starter/score-importance)<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/score-importance"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/score-importance/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/jezweb/vite-flare-starter/score-importance"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/score-importance.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 | $0.00030 | $0.00573 |
| Opus 5 | $0.00015 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
score-importance 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score Importance
Purpose
inbox_add accepts an importance field — high, medium, or low. Without consistency, what one routine calls "high" another calls "medium" and the user stops trusting the field.
This skill defines what each level means so all your routines agree.
Definitions
high
Action is needed within the day. If the user ignores it, something will break or get worse.
Examples:
- Backup failed. Quota exceeded. Auth expired on a connector the user relies on.
- A new high-value lead replied; a hot conversation needs follow-up by EOD.
- Cost overrun on a paid integration.
- Security signal: unfamiliar login, unusual API rate.
medium
Action is helpful within the week. Not blocking, but skipping has a cost.
Examples:
- Stuck items (tickets, leads, drafts) older than the user's threshold.
- A meeting summary the user might want to skim before tomorrow.
- A summary of activity the user usually checks daily but missed today.
- A trend (search volume, engagement) worth knowing about.
low
FYI. Skipping has no cost. The user is happy to know but won't act.
Examples:
- A YouTube/article summary; "the X talk you bookmarked is now public".
- Counters: "you sent 14 messages today, your average is 11".
- Routine status: "all 12 sites checked, all healthy" (when the user wants to see proof of work).
Heuristics
| Signal | Suggests |
|---|---|
| Time-bound (deadline, expiry) | high |
| Money-bound (cost, revenue) | high or medium |
| Failure / regression | high |
| Volume / count change | medium or low |
| New content (article, video, message) | low (unless from a key relationship) |
| "Should I look at this?" — user-paced | medium or low |
Confidence
Pair importance with confidence (0..1). High confidence + medium importance is more actionable than low confidence + high importance. If you're not sure something matters, lean low + add a reasoning line so the user can confirm.
Anti-patterns
- Don't mark routine work
highto get the user's attention. The user disables routines that cry wolf. - Don't use
lowfor things you secretly think arehigh— that's still crying wolf, just inverted. - Don't fill
importanceif you genuinely don't know. Leave it null and let the user filter.
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.
- 10d ago First seen · 66 lines · 30 tokens per session scan A b03cd3af6a30
score-importance is a skill published in the GitHub repository jezweb/vite-flare-starter (48 stars, last pushed 15d ago), licensed MIT. It adds 30 tokens to every session and 573 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.