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 PsychQuant/che-ical-mcp --skill troubleshoot-tccgit clone --depth 1 https://github.com/PsychQuant/che-ical-mcpWrote 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/psychquant/che-ical-mcp/troubleshoot-tcc)<a href="https://agentmods.dev/skills/psychquant/che-ical-mcp/troubleshoot-tcc"><img src="https://agentmods.dev/badge/skills/psychquant/che-ical-mcp/troubleshoot-tcc/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/psychquant/che-ical-mcp/troubleshoot-tcc"><img src="https://agentmods.dev/badge/skills/psychquant/che-ical-mcp/troubleshoot-tcc.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 | $0.00119 | $0.04592 |
| Opus 5.5 | $0.00048 | $0.01837 |
| Sonnet 5.5 | $0.00024 | $0.00918 |
| Haiku 4.5 | $0.00012 | $0.00459 |
Grade A, and why
troubleshoot-tcc 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 yesterday.
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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot TCC permissions for che-ical-mcp
This skill is the first thing to try when calendar / reminder tools fail. Most "calendar tools don't work" reports are TCC (Transparency, Consent & Control) state issues rather than code bugs.
v1.22.0+: under Claude Code, CheICalMCP is its own responsible process (#343) — read this first
- TCC checks only the responsible process. Measured in #343 with one variable changed: the same
~/bin/CheICalMCP --print-tcc-pathreadfullAccesswhen spawned under VS Code, although CheICalMCP's own grant was empty at the time, andnotDeterminedwhen spawned disclaimed (CheICalMCP responsible for itself). The host's grant alone decided the first result; CheICalMCP's own grant alone decided the second. - From v1.22.0 the binary re-execs in place as its own responsible process only when the process macOS reports as responsible is Claude Code (its native executable under
~/.local/share/claude/versions/<ver>, orClaudeCode.app):posix_spawn+POSIX_SPAWN_SETEXEC+ disclaim, the same call Claude Desktop'sdisclaimermakes; pid and stdio unchanged. This covers the MCP server,--cli,--print-tcc-pathand--setup;--setupalso re-execs under any host, because it is the foreground action that creates CheICalMCP's own grant. Under Claude Code only theCheICalMCPentry matters. Every other host (Terminal, VS Code, Ghostty, ssh, cron, CI) keeps the behavior of v1.21.0 and earlier: no re-exec, the host's grant is checked, so the host-layer entry still applies there. Host-layer entries (version numbers, Terminal, VS Code) also apply withCHE_ICAL_MCP_NO_DISCLAIM=1or on v1.21.0 and earlier. - Trade-off: where the re-exec happens, macOS checks CheICalMCP's grant, so once it is allowed, any process Claude Code launches that execs this binary (including
--cli) uses it without a separate consent, the same property the Claude Desktop.mcpbhas throughdisclaimer. - First run after upgrading (under Claude Code): the CheICalMCP grant may start as
notDetermined. Allow the macOS prompt for CheICalMCP, or run~/bin/CheICalMCP --setupin the foreground, which now printsAuthorization target: CheICalMCP (...)before asking. A background Claude Code session without a GUI cannot show the prompt. Only--setuphas been seen to show a prompt; whether server mode or--clishows one is unverified (CI does not cover reading the calendar through the new path). - To see which process macOS checks, run
--print-tcc-pathand read theTCC attributionline. Do not infer it frompsancestry: under the Claude Code daemon the parent chain does not show it. A spare-claimed session inherits the app that launched the daemon (e.g. VS Code), while a worker the daemon launches throughClaudeCode.appis its own responsible process, and the two chains look alike.
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.
- yesterday Changed · +12 lines f7a7f2f8f644
- 1mo ago First seen · 213 lines · 119 tokens per session scan A f306fd3a9051
troubleshoot-tcc is a skill published in the GitHub repository PsychQuant/che-ical-mcp (41 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 4,592 once invoked, about $0.0005 per session on Opus 5.5. 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
apple-calendar-cli
Manage Apple Calendar events on macOS with apple-calendar-cli. Use when listing calendars, finding or scheduling events, rescheduling meetings, or managing recurrence and alerts.
apple-pim
Native macOS personal information management for calendars, reminders, contacts, and local Mail.app. Use when the user wants to schedule meetings, create events, check their calendar, create or complete reminders, look up contacts, find someone's phone number or email, manage tasks and to-do lists, triage local…
cli-anything-nslogger
CLI harness for NSLogger — parse, filter, export, and monitor NSLogger log files (.rawnsloggerdata / .nsloggerdata).
sentry-app-setup
Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity.
burrow-system-tools
Diagnose and fix the user's Mac with Burrow's local MCP tools (burrowdoctor, burrowsnapshot, burrowtopprocesses, burrowprocessusage, burrowports, burrowanalyze, burrowdiskforecast, burrowdupes, burrowanomalies, burrowagentaudit, burrowclean, …). Use whenever the Mac is slow, hot, loud, low on disk, draining battery…
wispterm-diagnostics
Use when a user wants to report, troubleshoot, or collect context for a WispTerm issue, including crashes, rendering/DPI glitches, high CPU, keyboard/input bugs, selection/copy/scrolling, SSH/SCP failures, SSH image preview failures, HTML preview/browser panel failures, SSH disconnects such as…