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.
git clone --depth 1 https://github.com/thettwe/nyannWrote 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/commands/thettwe/nyann/watch)<a href="https://agentmods.dev/commands/thettwe/nyann/watch"><img src="https://agentmods.dev/badge/commands/thettwe/nyann/watch/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/commands/thettwe/nyann/watch"><img src="https://agentmods.dev/badge/commands/thettwe/nyann/watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00067 | $0.00620 |
| Opus 5.5 | $0.00027 | $0.00248 |
| Sonnet 5.5 | $0.00013 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
nyann:watch 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 1mo 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/watch/SKILL.md for the full flow.
/nyann:watch
Wraps bin/ci-sentinel.sh (one-shot), bin/sentinel-daemon.sh
(supervised background daemon), and bin/sentinel-aggregate.sh
(multi-repo watch-list). Default: polls one or all open PRs once per
call, writing a Notification entry whenever a check status or review
status transitions. With --daemon (opt-in), starts a launchd / systemd
/ nohup-supervised loop that survives the session and self-caps at
--max-runtime (8h). --stop halts either mode.
For watching PRs across several repos, --add/--remove/--list
manage a watch-list at ~/.claude/nyann/watch-list.json, and the
aggregate scheduler (sentinel-aggregate.sh --poll) polls every watched
repo under one globally rate-limit-aware loop. Read the merged,
repo-tagged view across all watched repos with
bin/read-notifications.sh --all. See skills/watch/SKILL.md Step 4.
Surfaces queued notifications via bin/read-notifications.sh on the next
session-start hook fire.
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.
- 1mo ago First seen · 57 lines · 67 tokens per session scan A abda3070cd0b
nyann:watch is a command published in the GitHub repository thettwe/nyann (7 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 620 once invoked, about $0.0003 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 2026-08-31.
Other commands, from other repositories
watch-ci
Monitor CI/CD pipeline and automatically fix failures. Watches GitHub Actions runs and applies fixes when tests fail.
setup-cicd
Configure real CI/CD pipelines in GitHub Actions, Azure Pipelines, or GitLab CI from the blueprint.
well-architected
Six-pillar well-architected review with scores and improvement roadmap.
sdlc-deploy
Phase 5 — Infrastructure & Deployment. Spawns devops-engineer and cloud-engineer to design CI/CD, containerization, and cloud infrastructure.
sdlc-release
Release planning and rollout - versioning, staging, gradual deployment, rollback.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.