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 conallob/o11y-analysis-tools --skill promql-codygit clone --depth 1 https://github.com/conallob/o11y-analysis-toolsWrote 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/conallob/o11y-analysis-tools/promql-cody)<a href="https://agentmods.dev/skills/conallob/o11y-analysis-tools/promql-cody"><img src="https://agentmods.dev/badge/skills/conallob/o11y-analysis-tools/promql-cody/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/conallob/o11y-analysis-tools/promql-cody"><img src="https://agentmods.dev/badge/skills/conallob/o11y-analysis-tools/promql-cody.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 | $0.00176 | $0.01696 |
| Opus 5 | $0.00088 | $0.00848 |
| Sonnet 5 | $0.00035 | $0.00339 |
| Haiku 4.5 | $0.00018 | $0.00170 |
Grade A, and why
promql-cody 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromQL-Cody
In memoriam. This skill is named after and dedicated to the late Cody Smith
PromQL-Cody is the unified Agent Skill for o11y-analysis-tools: it
teaches an agent how to use all six PromQL/Alertmanager CLIs in this repo
together — which are safe to run unattended, which need a human in the
loop, and what order they belong in. Load the per-tool skill
(skills/<tool>/SKILL.md) for the exact flags and output format of
whichever tool this points you at; this skill is the map, not the detail.
The six tools at a glance
| Skill | Purpose | Hermetic? | Best run | External dependency |
|---|---|---|---|---|
promql-fmt |
Format/validate PromQL multiline style + best-practice lint | Yes | Interactive and CI | none |
label-check |
Enforce required labels on expressions/alerts | Yes | Interactive and CI | none |
autogen-promql-tests |
Generate promtool-style unit test skeletons |
Yes | Interactive, to bootstrap coverage | none |
e2e-alertmanager-test |
Render alert notifications (email/Slack/JSON) end-to-end — a "print preview" for alerts | Yes*, with a skeleton config (see its skill) | CI, producing a diffable artifact; also useful interactively | an ephemeral Alertmanager + a Prometheus unit-test file |
alert-hysteresis |
Recommend for: duration tuning from real firing history |
No | Interactive, as needed | live Prometheus with historical ALERTS data |
stale-alerts-analyzer |
Flag alerts that rarely/never fire — "dead code analysis" for alerts | No | Interactive, periodic cleanup | live Prometheus with historical ALERTS data |
* Only when its ephemeral Alertmanager is loaded with a skeleton config that overrides receiver connection details. Pointed at a real/unmodified Alertmanager config, it can dispatch real notifications and is not hermetic.
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.
- 10d ago First seen · 106 lines · 176 tokens per session scan A 6e429da6464f
promql-cody is a skill published in the GitHub repository conallob/o11y-analysis-tools (4 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 176 tokens to every session and 1,696 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
monitoring-observability
Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (astype, scorecurrentspan, shouldexportspan, LangfuseMedia), and drift detection. Use when adding logging, metrics, distributed tracing, LLM cost tracking, or quality drift monitoring.
host_bash
A read-only shell skill for examining files and running diagnostic commands in a restricted environment. A shell is a text interface for operating-system commands.
host_restart_service
A tool for restarting approved systemd services, which are background programs managed by Linux's service manager.
golang-observability-opentelemetry
Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.
monitoring-expert
Expert-level monitoring and observability with Prometheus, Grafana, logging, and alerting. Use when the user mentions observability, Prometheus, Grafana, logging, metrics, or alerting, or when the task involves The Three Pillars of Observability, Monitoring Fundamentals, Prometheus Configuration, or Alert Rules.
prometheus-expert
Expert-level Prometheus monitoring, metrics collection, PromQL queries, alerting, and production operations. Use when the user mentions monitoring, metrics, observability, alerting, or PromQL, or when the task involves Prometheus Architecture, Installation on Kubernetes, ServiceMonitor, or PromQL Queries.