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 agentmods add commands/notque/vexjoy-agent/github-notificationsgit clone --depth 1 https://github.com/notque/vexjoy-agentWhat 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 | $0.00014 | $0.00202 |
| Opus 5 | $0.00007 | $0.00101 |
| Sonnet 5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
github-notifications scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Triage GitHub notifications: fetch, classify, report actions needed.
Usage: /github-notifications [--mark-read] [--save]
Default: report-only (shows what needs attention, doesn't modify anything) --mark-read: also mark informational notifications as read --save: save report to ~/.claude/reports/notifications/
Invokes: scripts/github-notification-triage.py
Instructions for Claude
Arguments: "$ARGUMENTS"
Parse arguments from $ARGUMENTS, then run:
python3 scripts/github-notification-triage.py $ARGUMENTS
Present the output to the user. If the report includes informational notifications and --mark-read was not passed, ask the user if they want to clear them.
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.
- 2d ago First seen · 28 lines · 14 tokens per session scan A 14b7a2a584e7
github-notifications is a command published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 202 once invoked, about $0.0001 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 commands, from other repositories
test-tdd
Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.
workflow-foundation-to-design
Run the end-to-end Foundation Sprint + Design Sprint workflow with narrative handoff.
plan-workflow
Generate a skill chain plan for a high-level goal by analyzing the skills registry for input/output compatibility.
find
Search the 1ai-skills library for the skill matching the user's request.
brainstorm-divergent
Generate genuinely different ideas across the solution space, then converge on the strongest few.
overlay-sync
Scaffold/sync this project's overlay skills from .claude/apple-overlays.json, idempotently. Add --check for a no-write CI drift check.