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 agentmods add skills/datatorag/mcp-gateway/ops-debuggingnpx skills add datatorag/mcp-gateway --skill ops-debugginggit clone --depth 1 https://github.com/datatorag/mcp-gatewayWhat 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 | $0.00050 | $0.02972 |
| Opus 5 | $0.00025 | $0.01486 |
| Sonnet 5 | $0.00010 | $0.00594 |
| Haiku 4.5 | $0.00005 | $0.00297 |
Grade A, and why
ops-debugging 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
step, rebuild command, health-check curl, plugin reinstall exec, log-tailing, How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops Debugging — Production Gateway
Diagnose and operate the production gateway without hard-coding any infrastructure details in this file. This skill lives in a public repo; live values (host, SSH key, ports beyond what's already public in the compose files, profile names) come from private memory or the deploy/db-query skills, never from here.
Sources of truth
Don't duplicate these — read them first, then come back here for the gap:
- Deploy skill (
.claude/skills/deploy/SKILL.md) — SSH access,.envrender step, rebuild command, health-check curl, plugin reinstall exec, log-tailing, its own 5-item Troubleshooting section. - db-query skill (
.claude/skills/db-query/SKILL.md) — how to query prod (Neon, via Neon MCP) vs local dev (docker exec psql), safety rails, canned recipes including the tool-registry query. - Memory refs for live values:
reference_mcp_gateway_instance(host/region),reference_plugin_registry(installed plugins, reinstall notes),reference_neon_database(prod project id/region).
This skill only adds what those don't cover: the full plugin re-discovery recipe (deploy skill stops at "see reference_plugin_registry for details"), a symptom-first failure-mode table, and verification patterns that combine health checks + DB state.
Plugin update + tool re-discovery
When a plugin's tool set changes (new/renamed/removed tools) and a rebuild alone
won't fix the tools table, run the full re-discovery recipe. Proven in prod
2026-07-18.
-
Pull + build the plugin inside its running container (see deploy skill step 5 for the
git pull && pnpm install && npx tscexec). -
Restart the gateway so the plugin child process picks up the new build.
-
Run a re-discovery script from inside the gateway container — it must execute from
/app/apps/gateway(module resolution for@modelcontextprotocol/sdkand thepostgresdriver fails from/tmpor other paths):docker exec -i <gateway-container> bash -c \ 'cat > /app/apps/gateway/rediscover.mjs && cd /app/apps/gateway && node rediscover.mjs; rm -f /app/apps/gateway/rediscover.mjs' < rediscover.mjs
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.
- 2d ago First seen · 220 lines · 50 tokens per session scan A b859cd860e48
ops-debugging is a skill published in the GitHub repository datatorag/mcp-gateway (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 2,972 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
reproduce-issue
The single skill for reproducing an nx issue. Given a GitHub issue number (human entry) OR explicit repro parameters (agent entry), it runs the reproduction ENTIRELY inside an isolated Docker sandbox — gVisor on Linux, the Docker VM on macOS — so the untrusted repro's install scripts and commands never execute on the…
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.
atmos-aws-ecr
AWS ECR commands in Atmos: atmos aws ecr login, ECR auth integrations, Docker credential writes, registry login via identity or explicit registry.
windows-builder
Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.
release-openclaw-plugin-testing
Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.