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 skills add gotempsh/temps --skill start-temps-clustergit clone --depth 1 https://github.com/gotempsh/tempsWrote 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/skills/gotempsh/temps/start-temps-cluster)<a href="https://agentmods.dev/skills/gotempsh/temps/start-temps-cluster"><img src="https://agentmods.dev/badge/skills/gotempsh/temps/start-temps-cluster/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/skills/gotempsh/temps/start-temps-cluster"><img src="https://agentmods.dev/badge/skills/gotempsh/temps/start-temps-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 171 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 177 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Excessive Agency · line 84 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 126 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium MCP Rug Pull · line 151 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 155 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Data Exfiltration · line 171 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 177 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium MCP Rug Pull · line 189 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00204 | $0.04633 |
| Opus 5.5 | $0.00082 | $0.01853 |
| Sonnet 5.5 | $0.00041 | $0.00927 |
| Haiku 4.5 | $0.00020 | $0.00463 |
Grade A, and why
start-temps-cluster scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}\n' http://localhost/api/health How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a local multi-node Temps cluster (Docker-in-Docker)
Wraps tools/dev-cluster/ — a docker-compose harness that runs a real Temps
control plane plus 3 worker nodes, each a privileged DinD container, with the
actual overlay network (VXLAN, compute_cidr allocation, cluster DNS) wired
up exactly as it would be on real hardware. Use this whenever a fix or feature
needs more than one node to prove anything — single-node start-temps
cannot exercise cross-node scheduling, the overlay, or cluster DNS at all.
Topology
┌──── temps-underlay (10.42.0.0/24, docker bridge, the "VPC") ────┐
│ │
│ postgres 10.42.0.5 (TimescaleDB pg18, internal) │
│ control-plane 10.42.0.10 DinD + `temps serve` │
│ host ports 80 → 80, 443 → 443 (NOT 8080 — see Gotcha below) │
│ │
│ worker-1 10.42.0.21 worker-2 10.42.0.22 worker-3 10.42.0.23│
│ each: privileged DinD + `temps agent`, own dockerd │
└──────────────────────────────────────────────────────────────────┘
Allocator carves /24s from 172.20.0.0/16, one per worker:
worker-1 → 172.20.0.0/24
worker-2 → 172.20.1.0/24
worker-3 → 172.20.2.0/24
Cross-node container traffic flows over a VXLAN tunnel pinned to the
underlay IPs above. Within-node traffic uses the unchanged
`temps-app-network` Docker bridge (same as single-node temps).
The temps source tree is bind-mounted read-write at /workspace inside every
DinD container, and cargo build --bin temps runs inside Linux — no
cross-compiling from macOS. The cluster builds from whichever checkout you
run ./dev-cluster in. cd into the right worktree first if you're testing
a fix that isn't on the checkout's current branch.
Prerequisites
- Docker Desktop (or any Linux Docker host) running —
docker versionmust succeed. - ~3 GB free RAM, ~5 GB free disk (compiled binary cache + 4 worker volumes + TimescaleDB volume).
GeoLite2-City.mmdbat the repo root of the checkout you're running from (<checkout>/GeoLite2-City.mmdb, gitignored) — the proxy plugin refuses to start without it. Download it from MaxMind's GeoLite2 program (free registration required) and place it at the repo root. If you keep multiple worktrees of this repo, copying the file between them is faster than downloading it again.
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 · 322 lines · 204 tokens per session scan A c34a940d3605
start-temps-cluster is a skill published in the GitHub repository gotempsh/temps (851 stars, last pushed today), licensed Apache-2.0. It adds 204 tokens to every session and 4,633 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
releasing-prod
A controlled process for deploying already tested changes to the production environment. Production is the live environment used by users, and this process includes owner approval, database migration checks, deployment, and smoke tests.
docker-via-wsl
Use when YOU (the AI agent) are running on Windows OUTSIDE WSL (Git Bash/MSYS/PowerShell shell) and need to run ANY docker / docker compose command. Docker Desktop runs on the WSL2 engine, so commands must be re-issued INSIDE WSL via wsl.exe -- running them from the Windows shell on a network/SMB drive (Z:, UNC)…
self-improve
Write features, fix bugs, and create PRs for the NanoClawbster codebase. Works in an isolated dev workspace, pushes via Composio (CI validates on GitHub Actions), and deploys after user approval.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
ci-cd
CI/CD pipelines for GitHub Actions and Docker-based deployments — lint, test, build, push, deploy stages; environment secrets; branch-gated workflows; health-check rollbacks; and PM2/systemd service restarts.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.