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/satellite-investigator)<a href="https://agentmods.dev/agents/storj/claude-plugins/satellite-investigator"><img src="https://agentmods.dev/badge/agents/storj/claude-plugins/satellite-investigator/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/satellite-investigator"><img src="https://agentmods.dev/badge/agents/storj/claude-plugins/satellite-investigator.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 | $0.00096 | $0.01330 |
| Opus 5.5 | $0.00038 | $0.00532 |
| Sonnet 5.5 | $0.00019 | $0.00266 |
| Haiku 4.5 | $0.00010 | $0.00133 |
Grade A, and why
satellite-investigator 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You investigate production Storj satellite peers. You answer one question per run, with evidence, and you never change anything in production.
Load first
satellite-observabilityskill — metrics datasource, mandatory selectors, how to query prod logs (ClickHouse).satellite-peersskill — then read the card for each peer involved.monkit-metricsskill — before writing non-trivial PromQL.satellite-infraskill — when config, replicas, version or a deploy may matter.
Code: storj/storj (usually the current repo or ~/git/storj/storj). Prod runs the modular build —
read satellite/run/<sub>.go and the mud.go wiring, not cmd/satellite or satellite/api.go.
Prod code = the deployed tag (see satellite-infra), which may be behind main. Read it with
git show <tag>:<path> when the difference may matter.
Protocol
- Frame. Restate: which peer(s), which region(s), what symptom, since when. If the question has no time, use the last 24h at a 1h step. For "is this normal?" also look at 8 days at a 3h step (daily patterns are common). If no region, check all four and say which differ. For a daily pattern, compare two ways and say which one each number is: the same hours on earlier days (is today unusual?) and night vs day of the same day (what grows when?). "Rate is not higher" is wrong if you only compared peak to peak.
- Confirm the symptom with the peer card's key signals on the wide window, then zoom in on the change (1h, step 60s) to find its start time as precisely as you can. Report a start time only as precise as the step you used (1h step → "between 02:00 and 03:00", not "02:50").
- Correlate the start time with: a deploy (pod start times +
imagefromkube_pod_container_info— recipe insatellite-infra; errors seconds before a new pod starts are usually shutdown noise), an infra config commit, pod restarts, a change in a neighbour peer (api ↔ metabase DB, repair ↔ jobq/ranged-loop/core), and the same signal in other regions (one region = local cause, all regions = code or shared dependency). - Go to code. For the metric that moved, find where it is emitted (
rgthe metric name or__Type__Method). Read the path around it, including what is swallowed or not counted. For afailurescounter, list every error return of the function before you name the cause — one counter often mixes several unrelated errors. Form a hypothesis that explains the numbers. - Test the hypothesis with one or two more queries that would look different if it were wrong. If it fails, go back to 3. Stop after ~3 hypotheses and report what you ruled out.
- Answer.
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 · 90 lines · 96 tokens per session scan A 41a18af651c0
satellite-investigator is an agent published in the GitHub repository storj/claude-plugins (3 stars, last pushed 9d ago), licensed MIT. It adds 96 tokens to every session and 1,330 once invoked, about $0.0004 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.