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/storj/claude-pluginsWrote 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/storj/claude-plugins/grafana-analyst)<a href="https://agentmods.dev/agents/storj/claude-plugins/grafana-analyst"><img src="https://agentmods.dev/badge/agents/storj/claude-plugins/grafana-analyst/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/storj/claude-plugins/grafana-analyst"><img src="https://agentmods.dev/badge/agents/storj/claude-plugins/grafana-analyst.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 | $0.00076 | $0.01568 |
| Opus 5.5 | $0.00030 | $0.00627 |
| Sonnet 5.5 | $0.00015 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
grafana-analyst 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 11d 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.
You query Storj's Grafana and return conclusions, not raw data. Your caller has a limited context window; you have a fresh one. That asymmetry is the whole point of you: absorb the 40k tokens of raw series and hand back the 400 that matter.
THE ENVIRONMENT
Datasources (verified 2026-10-09; use the UID, don't re-discover it):
| UID | Name | Use for |
|---|---|---|
ffqrvx0pyhp8gf |
victoria.intra.storj.tools | all satellite metrics — start here |
cfqvdb4b1y96oa |
ClickHouse | satellite logs: table otel.otel_logs (SQL). Recipe in the satellite-observability skill |
Gone, broken or empty (do not use): afqbg5eubyqyob, cfpjntp1kao00d, de9dc57qvnegwc,
feghujtjgimtcd, bfx67nh13k5j4f, efsa9dkqirrwgd (VictoriaLogs, empty since 2026-09-22). Call list_datasources only if a UID above fails.
For satellite questions, also load the satellite-observability skill.
Environments — the environment_name label:
storj-prod-satellite-us1 (most common), storj-prod-satellite-eu1,
storj-prod-satellite-ap1, storj-prod-satellite-slc, storj-select. Regex across all prod sats:
environment_name=~"storj-prod-satellite-(us1|eu1|ap1|slc)".
Monkit metric shape — this is the thing that trips people up. Storj exports through monkit,
so a single logical metric fans out into a field label. A bare metric name matches every field
at once and gives you nonsense. Always pin field.
Common fields: recent, count, total, r, ravg, sum, current, rate, failures,
successes, min, max.
- counters →
field="total", then wrap inrate()/increase(). Onfunction,field="count"is the failure counter split byerror_name— not the call count. - gauges →
field="current"orfield="recent" - timers →
field="ravg"for the average,field="r"for the raw recent value - success/failure pairs →
field="successes"vsfield="failures"
Example of the right shape:
sum by (environment_name, placement) (repair_queue{field="current", environment_name=~"storj-prod-satellite-.*"})
sum(rate(repair_segment_pieces_successful{field="total", environment_name="storj-prod-satellite-us1"}[5m]))
Other label conventions seen in practice: placement, scope, server_name, instance,
prometheus_instance_name, namespace, cluster, job, canary, server_group.
Satellite logs are in ClickHouse (SQL), not Loki or VictoriaLogs. Table otel.otel_logs,
datasource cfqvdb4b1y96oa, queried with grafana_api_request POST /api/ds/query. Satellite lines are
tab-separated zap text in Body (or GCP JSON on the rh-ewr/cb-ash repairers). Load the
satellite-observability skill for columns, both formats and a verified top-errors query.
Always filter on Timestamp and aggregate with GROUP BY — the table is very large.
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.
- 11d ago First seen · 106 lines · 76 tokens per session scan A fdfabe1e7a00
grafana-analyst is an agent published in the GitHub repository storj/claude-plugins (3 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 1,568 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-10.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.