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/thettwe/nyann/settingsgit clone --depth 1 https://github.com/thettwe/nyannWhat 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 | $0.00032 | $0.00384 |
| Opus 5 | $0.00016 | $0.00192 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
nyann:settings 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
Plugin root: This is a Claude Code plugin, NOT a CLI tool. Do NOT
search via which, npm list, pip list, or brew list. This file
is at <plugin_root>/commands/. All scripts: <plugin_root>/bin/.
Read skills/settings/SKILL.md for the full flow.
/nyann:settings
Wraps bin/settings.sh. Interactive menu over the preferences managed in
~/.claude/nyann/preferences.json — core defaults, proactive toggles, and the
opt-in external notification delivery channels (Slack/Discord/webhook/email).
- No arguments → show the current table, then ask "Which setting to
change?" via
AskUserQuestion. <key> <value>(two positional args) → bypass the menu and runbin/settings.sh --set <key> <value>directly.
Delivery endpoints are secrets: the notifications.delivery.* *_env keys
store only the NAME of an environment variable (e.g. NYANN_SLACK_WEBHOOK),
never the URL. bin/settings.sh refuses a literal http(s):// value.
Use for ongoing preference management. Use /nyann:setup only for
first-run onboarding.
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 · 37 lines · 32 tokens per session scan A 88cfdb5e75d7
nyann:settings is a command published in the GitHub repository thettwe/nyann (6 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 384 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 2026-08-31.
Other commands, from other repositories
create-namespace
Slash command that creates a new namespace file under system/namespaces/ in the personal repo, with lifecyclestate: scratch.
oss
Daily OSS contribution check - uses CLI with --json for structured data.
plan
Show diff between YAML and current GitHub state. No mutations are made.
sicario.verify
Run deterministic verification.
closeout
Close out a UNITARES workspace before final response.
reset
Reset DESIGN-OPS configuration to start fresh.