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 | $0.00092 | $0.00538 |
| Opus 5 | $0.00046 | $0.00269 |
| Sonnet 5 | $0.00018 | $0.00108 |
| Haiku 4.5 | $0.00009 | $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 9d 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.
- 9d 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 1mo ago), licensed MIT. It adds 92 tokens to every session and 538 once invoked, about $0.0005 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 agents, from other repositories
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…
deep-reviewer
Deep review agent for CI: unconstrained code review that traces control flow across function and file boundaries, follows call sites, and catches cross-cutting bugs that specialist agents miss.
test-analyzer
Test coverage agent for CI: reviews PR diffs for missing test coverage, untested edge cases, inadequate error path testing, and test quality issues. Focuses on behavioral coverage over line metrics.
guidelines-checker
Guidelines compliance agent for CI: checks CLAUDE.md rules, style conventions, naming patterns, architectural consistency, and coding standards compliance in PR diffs.
team_lead_agent
A team-coordination agent for running a complete research project from defining the question through literature review, coding, experiments, iteration, paper writing, and delivery.
critic_agent
A critical-review agent for short stories that scores the draft’s opening, characters, structure, scenes, language, emotional effect, and originality. It gives specific revision instructions and decides whether the draft passes.