nyann:fleet

A read-only dashboard for a registered group of local Git repositories. It lists each repository's health score, trend, drift findings, and most serious problem.

In plain words
What is it for?
Use it to add, remove, scan, or prune repositories in the registry and to review their combined health before making fixes.
Why use it?
It replaces separate repository checks with one cross-repository view, making it easier to find which projects need attention first.

Command

Install

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.

agentmods
npx agentmods add commands/thettwe/nyann/fleet
Clone the repo
git clone --depth 1 https://github.com/thettwe/nyann
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.00605
Opus 5 $0.00032 $0.00302
Sonnet 5 $0.00013 $0.00121
Haiku 4.5 $0.00006 $0.00060

Measured 2d ago against content hash 9ede5a69fe1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nyann:fleet 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.

commands/fleet.md · 52 lines

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/fleet/SKILL.md for the full flow.

/nyann:fleet

Wraps bin/fleet.sh (registry CRUD: --add/--remove/--list/--scan/ --prune/--suggest-org) and bin/fleet-doctor.sh (bulk audit + dashboard). The registry lives at ~/.claude/nyann/fleet.json — LOCAL working-copy paths, distinct from the sentinel watch-list (GitHub slugs); an entry's optional repo slug joins the two (--watch mirrors it).

Dashboard default is a live per-repo doctor pass (worst-of exit codes 0/4/5); --cached reads persisted memory/health.json scores instantly with staleness flags; --drift/--explain roll repo-tagged findings up into one view. Registry scans and prunes preview first and only write with --apply.

See also:

  • /nyann:fleet-retrofit — bulk remediation once the dashboard shows drift.
  • /nyann:doctor — the single-repo deep dive.
  • /nyann:watch — CI/PR watching across repos (remote state, not governance).
Changes

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.

  1. 2d ago First seen · 52 lines · 63 tokens per session scan A 9ede5a69fe1f

Subscribe to this mod's changes

nyann:fleet is a command published in the GitHub repository thettwe/nyann (6 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 605 once invoked, about $0.0003 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.