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.
git clone --depth 1 https://github.com/air-gapped/skillsWrote 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/plugins/air-gapped/skills/observability)<a href="https://agentmods.dev/plugins/air-gapped/skills/observability"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/observability/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/plugins/air-gapped/skills/observability"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
observability 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 12d 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
{
"name": "observability",
"source": "./",
"description": "Observability suite — metrics: Prometheus, Grafana Mimir, and Grafana reference for agents querying metrics, writing PromQL, building and fixing dashboards, and reasoning about SLOs, KPIs, and burn-rate alerting, plus the community, air-gapped mimir-distributed Helm upgrade methodology (chart↔app co-pinned ladder, the classic-vs-ingest-storage/Kafka decision, the nginx→gateway rename that silently moves the proxy's DNS name, rollout-operator sequencing and abort levers, per-hop verification, and air-gap image/CRD/egress staging); and logs: the kube-logging logging-operator (16-CRD Fluent Bit→fluentd/syslog-ng pipeline, JSON/CRI parsing, routing, buffers, upgrade floor 6.7.0) plus rancher-logging-exit — the air-gap-first migration off Rancher's frozen bundled rancher-logging chart (CVE-2026-54680, release-secret cutover, CR compatibility); and hardware metrics: snmp-exporter — Prometheus snmp_exporter v0.30.x best practices (generator.yml module curation, the never-walk-a-whole-enterprise-subtree rule, SNMPv2c/v3 auth, timeout math, Kubernetes Probe/ScrapeConfig deployment, local docker testing, worked device references for Dell iDRAC 9/10, Cisco CBS/Catalyst, NVIDIA/Mellanox Onyx, Ubiquiti UniFi).",
"version": "0.20261004.40",
"author": {
"name": "Jörgen"
},
"license": "MIT",
"skills": [
"./.claude/skills/prometheus-mimir-grafana",
"./.claude/skills/mimir-upgrade",
"./.claude/skills/snmp-exporter",
"./.claude/skills/logging-operator",
"./.claude/skills/rancher-logging-exit"
],
"strict": false,
"category": "observability",
"tags": [
"prometheus",
"mimir",
"grafana",
"promql",
"observability",
"metrics",
"logging",
"logging-operator",
"fluentd",
"fluent-bit",
"rancher",
"snmp",
"snmp-exporter",
"network-monitoring",
"slo",
"sre",
"upgrade",
"helm",
"air-gap"
]
}What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 902 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#observability in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago Changed 52dab6ebaa3b
- 24d ago Changed 366705509cff
- 1mo ago Changed 74d7a36143c9
- 1mo ago Changed 8f61879077cd
- 1mo ago First seen · 40 lines scan A b62f86d01af4
observability is a plugin published in the GitHub repository air-gapped/skills (5 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
issue-to-pr
Take a GitHub issue (bare, or tracked on a Project board) from triage to a merge-ready PR through a gated, worktree-isolated pipeline that scales its depth to the task and asks at most one batched question. The gates hold every run: design hardening, tests green, code review clean. Once you approve the PR in-session…
claude-md-slim
Shrink an oversized or stale CLAUDE.md by moving subsystem detail into path-scoped .claude/rules/ files, with scripts that measure the loaded size against the documented 200-line budget and prove the extraction lost nothing.
humanizer
Remove AI-generation patterns from English or Russian text — auto-detects language and applies a matching MIT-licensed ruleset (33-pattern EN from blader/humanizer, 54-pattern RU from ilyautov/humanizer-ru) with explicit override and mixed-text handling.
agent-dispatch
Start issue-to-pr runs from GitHub labels on your own machine: a scheduled tick picks the issue you labelled agent, or the one you replied on, and runs it headless under your own Claude Code or Codex login, on Windows, macOS or Linux.
agent-teams
Set up and orchestrate Claude Code agent teams - multiple instances working together with shared tasks, messaging, and coordination.
codex-collaboration
Cross-model collaboration between Claude and Codex — sequential drive/validate/act loops and parallel dual review with triage.