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 terrylica/cc-skills --skill monitor-inboxgit clone --depth 1 https://github.com/terrylica/cc-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/terrylica/cc-skills/monitor-inbox)<a href="https://agentmods.dev/skills/terrylica/cc-skills/monitor-inbox"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/monitor-inbox/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/terrylica/cc-skills/monitor-inbox"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/monitor-inbox.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 | $0.00147 | $0.01216 |
| Opus 5 | $0.00073 | $0.00608 |
| Sonnet 5 | $0.00029 | $0.00243 |
| Haiku 4.5 | $0.00015 | $0.00122 |
Grade A, and why
monitor-inbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
monitor-inbox
Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
The rest of pushover-commander only sends; its audit log (po-audit.jsonl)
can never show what arrived. This skill wraps the Pushover Open Client API
(the REST surface the desktop/mobile apps use to receive) so a session can read
incoming notifications. Core: _lib/pushover_inbox.ts.
Model = on-demand pull (run pull when asked; no background daemon).
Commands
CORE="$(cc-plugin-root pushover-commander)/skills/_lib/pushover_inbox.ts"
# One-time, INTERACTIVE — mints a receive-device. Prompts for the Pushover ACCOUNT
# email + password (password is MASKED, used once in-memory, NEVER stored). Only the
# derived client secret + device_id are persisted, to the SCS vault scope `pushover`.
env -u HTTPS_PROXY -u HTTP_PROXY bun "$CORE" register [--name claude-mac] [--force]
# On demand — fetch new messages → append to po-inbox.jsonl → ack (update_highest).
env -u HTTPS_PROXY -u HTTP_PROXY bun "$CORE" pull [--json] [--limit N]
# Read back the local inbox (NO network).
bun "$CORE" list [--limit N] [--json]
# Health: creds present? device registered? API reachable / how many waiting?
env -u HTTPS_PROXY -u HTTP_PROXY bun "$CORE" doctor
One-time setup (operator must run register)
Only the operator can type the account password, so guide them to run register
themselves (or run it and let them type into the masked prompt). After that,
pull/list/doctor all work headlessly — no password, no Touch ID — because the
client secret + device_id live in the vault automation tier (agent-readable).
Secret handling (SCS doctrine — cc-skills/docs/self-custody-secrets.md)
| Secret | Class | Where it lives |
|---|---|---|
| Account email + password | crown jewel | masked prompt, in-memory only — never stored / never sent / never in argv or transcript |
client secret + device_id |
automation token | SCS vault scope pushover (agent-readable, so headless pull needs no prompt) |
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.
- 4d ago First seen · 88 lines · 147 tokens per session scan A 4858104349ac
monitor-inbox is a skill published in the GitHub repository terrylica/cc-skills (72 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 1,216 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
session-status
Analyzes current session state without any cleanup. Full mode (default): resolves the active plan file, reads plan checklist + TaskList, gathers unfinished work/issues from conversation history, and emits a /handoff-built next-session prompt. Mid-session mode (/session-status mid): a fast plain-language 'done vs…
ship
Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.
calendar
Google Calendar integration — check schedule, create events, daily briefings, proactive reminders. Triggers on "what's on my calendar", "add to calendar", "schedule a meeting", "when am I free", "daily briefing", or any calendar-related request.
native-first
Stack-agnostic discovery playbook for finding the native, non-custom way to do something before writing any script or wrapper. Use when tempted to write a shell/python/glue script, add a dependency, or build a custom helper — and whenever a script-guards hook blocks a script write. Climbs a fixed ladder (tool's own…
configure
Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.