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 OpenClaudia/openclaudia-skills --skill task-bannergit clone --depth 1 https://github.com/OpenClaudia/openclaudia-skillsWrote 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/openclaudia/openclaudia-skills/task-banner)<a href="https://agentmods.dev/skills/openclaudia/openclaudia-skills/task-banner"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/task-banner/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/openclaudia/openclaudia-skills/task-banner"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/task-banner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 21 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Tool Misuse · line 32 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 32 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Tool Misuse · line 54 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 44 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00071 | $0.00786 |
| Opus 5 | $0.00036 | $0.00393 |
| Sonnet 5 | $0.00014 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade B, and why
task-banner scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
2. Merge a `Stop` hook into `~/.claude/settings.json` (read the file first and preserve existing hooks): How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-banner
Show a large, always-on-top desktop banner when Claude Code finishes a turn — with a one-line summary of what was actually completed. Works even when macOS Notification Center silently drops osascript display notification calls (a common problem: the CLI has no Notification Center registration, so the command exits 0 but nothing shows).
The banner is a borderless Cocoa overlay window drawn by mac-overlay.js (a JXA script adapted from peon-ping), so no notification permissions are needed.
Requirements
- macOS (the overlay uses Cocoa via JXA /
osascript -l JavaScript) - Claude Code with hooks support
Setup
-
Copy
mac-overlay.jsfrom this skill directory to~/.claude/scripts/mac-overlay.js. -
Merge a
Stophook into~/.claude/settings.json(read the file first and preserve existing hooks):
{
"hooks": {
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "m=$(cat /tmp/claude-banner-msg 2>/dev/null); rm -f /tmp/claude-banner-msg; [ -f ~/.claude/banner.off ] || osascript -l JavaScript ~/.claude/scripts/mac-overlay.js \"${m:-Task done}\" blue \"\" 0 4 2>/dev/null || true",
"async": true
}
]
}
]
}
}
- To make the banner show what was finished (instead of the generic "Task done"), add this to your global agent instructions file (
~/.claude/CLAUDE.mdorAGENTS.md):
After finishing each task, write a short summary of what was completed to
/tmp/claude-banner-msg(e.g.printf 'Typecheck fixed and committed' > /tmp/claude-banner-msg). Identify the actual task; never use a generic "task done".
The Stop hook displays the message and deletes the file. If the file is absent, it falls back to "Task done".
Toggle (mute / unmute)
The hook checks a sentinel file — no config editing needed:
touch ~/.claude/banner.off # mute the banner
rm -f ~/.claude/banner.off # unmute
What ships with it
1 file 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.
- 9d ago First seen · 65 lines · 71 tokens per session scan B c499b11183aa
task-banner is a skill published in the GitHub repository OpenClaudia/openclaudia-skills (689 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 786 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
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.