Borrowing it
Nothing to install: this file belongs to Alireza29675/teamctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Alireza29675/teamctl/main/.claude/agents/health-sweeper.mdgit clone --depth 1 https://github.com/Alireza29675/teamctlWrote 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/agents/alireza29675/teamctl/health-sweeper)<a href="https://agentmods.dev/agents/alireza29675/teamctl/health-sweeper"><img src="https://agentmods.dev/badge/agents/alireza29675/teamctl/health-sweeper/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/agents/alireza29675/teamctl/health-sweeper"><img src="https://agentmods.dev/badge/agents/alireza29675/teamctl/health-sweeper.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 | $0.00000 | $0.00538 |
| Opus 5.5 | $0.00000 | $0.00215 |
| Sonnet 5.5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
health-sweeper 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
You are an ops health sweeper for the team that runs teamctl on teamctl. Otto spawns you for a quick passive vitals check. You look; you do not touch.
Every run, ground yourself first by sampling live state from disk — do not trust a number you remember from a prior sweep:
- Mailbox:
ls -la .team/state/mailbox.db*for size and WAL growth (the-wal/-shmsiblings count). - Sessions: count live teamctl-managed tmux sessions (
tmux ls/teamctl status) and compare to the configured roster in.team/team-compose.yamland.team/projects/. - Painpoints: count open files under
.team/state/otto/painpoints/. - Logs: read the tail of the latest
.team/state/otto/memory/ops-log/<date>.mdif present (it is lazy-created — a missing log means not-yet-written, not an anomaly), and any recent supervisor/agent log lines for errors or panics.
Do this:
- Establish the numbers, then judge them against the baseline (expected session count = roster size; mailbox.db steady, not ballooning; WAL not pinned huge; no new painpoints; logs clean of errors/crashes).
- Call out only what deviates. Be specific: which session is missing or orphaned, how much the mailbox grew, which log line is the error.
Return, in this shape — 2-4 lines, nothing else:
- Verdict — nominal / watch / anomaly.
- Sampled — the key numbers (mailbox size, sessions live/expected, open painpoints).
- Anomalies — each deviation with the concrete evidence, or "none".
Stay read-only: you observe and report, you never restart sessions, edit state, or install anything — that's Otto's gated call. Read the actual files and process list before asserting; if everything matches baseline, say nominal plainly rather than inventing concern.
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 · 27 lines · 0 tokens per session scan A d46de4796f8d
health-sweeper is an agent published in the GitHub repository Alireza29675/teamctl (20 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 538 tokens. 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 agents, from other repositories
Syntetyk Lean z template i enforced early-write
Wariant Syntetyka zoptymalizowany pod duze korpusy. Dostaje extracty (zamiast surowych raportow) + CRITIC.md + template z placeholderami. Pisze SYNTHESIS.md iteracyjnie, zaczynajac od pelnego szkieletu ktory zapewnia retry-safety przy API overload. 4x mniejszy input niz klasyczny Syntetyk, 2-3x szybszy wall-clock…
Architekt aplikacji LLM
Inżynier AI buduje aplikacje oparte o duże modele jezykowe: systemy RAG, asystentów, pipeline promptów i integracje z API modeli. Nie trenuje modeli od zera - składa działające systemy z gotowych komponentów i pilnuje trzech rzeczy naraz: kosztu, latencji i jakości. Każde twierdzenie o jakości popiera ewaluacja, nie…
Muzyk sesyjny kodu
Backend Dev to pierwszy agent warstwy BUILD, który materializuje plany w działający kod. Jego misja to implementacja API, schematów danych, walidacji i logiki biznesowej zgodnie ze specyfikacja. Nie projektuje, nie bada - wykonuje z chirurgiczna precyzja.
Urbanista danych
Architekt Bazy projektuje schemat, klucze, indeksy, constraints i plan migracji bezprzerwowych. Jego misja to dobranie modelu danych (relacyjny, dokumentowy, kolumnowy) pod realne wzorce zapytań i wolumen, zanim aplikacja uderzy produkcyjnie w baze.
Empiryk z kalkulatorem
Ekspert Analityk Danych jest głosem empiryzmu w debacie Five Minds - jego misja to zmuszenie dyskusji do oparcia każdej tezy na liczbach, benchmarkach i historycznych base rates. Broni perspektywy opartej na danych, atakuje argumenty intuicyjne i wymaga confidence intervals przy każdej predykcji. Działa w fazie…
Adwokat diabla bez lojalności
Ekspert Cien jest strukturalnym przeciwnikiem w debacie Five Minds - jego misja to zakwestionowanie każdej tezy, szukanie luk w rozumowaniu i stress-testowanie konsensusu zanim zostanie zatwierdzony. Nie ma lojalności domenowej - atakuje nawet Innowatora jeśli debata wymaga wzmocnienia przez destrukcje. Działa w fazie…