Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cptnbg/relay/plugin install relayWrote 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/commands/cptnbg/relay/relay-doctor)<a href="https://agentmods.dev/commands/cptnbg/relay/relay-doctor"><img src="https://agentmods.dev/badge/commands/cptnbg/relay/relay-doctor/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/commands/cptnbg/relay/relay-doctor"><img src="https://agentmods.dev/badge/commands/cptnbg/relay/relay-doctor.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 | $0.00008 | $0.00105 |
| Opus 5 | $0.00004 | $0.00053 |
| Sonnet 5 | $0.00002 | $0.00021 |
| Haiku 4.5 | $0.00001 | $0.00011 |
Grade A, and why
relay-doctor 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 9d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- relay-run — 89% identical, 6 lines differ
- relay-stop — 81% identical, 4 lines differ
What it actually says
Invoke the relay skill (Skill tool) and follow its doctor section.
Before running any relay script with Bash, resolve the plugin root exactly as the skill's "Resolve the plugin root" section specifies, and invoke scripts only through $RELAY_ROOT — never through a bare CLAUDE_PLUGIN_ROOT expansion. If the resolver prints "relay: FATAL", stop and tell the user to reinstall the plugin.
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.
- 9d ago First seen · 12 lines · 8 tokens per session scan A 2a185fd6896f
relay-doctor is a command published in the GitHub repository cptnbg/relay (1 stars, last pushed 9d ago), licensed MIT. It adds 8 tokens to every session and 105 once invoked, about $0.0000 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 commands, from other repositories
techdebt
Find and report technical debt in the codebase.
sdlc-verify
Phase 3 — Verify. Runs security-engineer always + performance-engineer when needsperformanceaudit is true. Reads build-handoff.md for clean context.
sdlc-diagnose
Automated Root-Cause Analysis (RCA) and surgical fix engine for massive enterprise codebases (up to 1.5M+ files).
debug-trace
Analyze error and trace execution path to identify root cause.
flow-explain
Expose execution paths of the workflow, describing triggers, conditional branches, and integration calls.
debug
AI-powered debugging: analyze errors, trace root causes, read logs, and auto-fix issues. Usage: /debug.