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 agentmods add commands/spree/agent-skills/doctorgit clone --depth 1 https://github.com/spree/agent-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/commands/spree/agent-skills/doctor)<a href="https://agentmods.dev/commands/spree/agent-skills/doctor"><img src="https://agentmods.dev/badge/commands/spree/agent-skills/doctor.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01037 |
| Opus 5 | $0.00013 | $0.00518 |
| Sonnet 5 | $0.00005 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
doctor scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Web responding** — `curl -fsS -o /dev/null -w '%{http_code}' http://localhost:<SPREE_PORT>/` (substitute the detected port) How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spree stack diagnosis
Run every check below in order against this project. Do not stop at the first failure — run all of them, then report. Judge each against its healthy state.
Pre-flight — detect the project flavor:
docker-compose.ymlat the root (create-spree-app / spree-starter): run the Docker checks below as written.- No Docker wiring but a Rails app with spree gems at the root (classic pre-5.4 app): skip checks 1–2, run everything else natively — replace
spree exec <cmd>with plain<cmd>from the app root, check the web on the portbin/dev/bin/rails suses (default 3000), and readbackend/Gemfile.lockasGemfile.lock. - Neither: not a Spree project — say so and stop.
Command routing (Docker flavors): prefer spree exec <cmd>; if the spree CLI isn't available, fall back to docker compose exec -T web <cmd>. If .env contains SPREE_PATH, this is a monorepo edge project — spree dev/spree build refuse there by design; remedies should say pnpm server:dev / pnpm server:build (run from the monorepo root) instead. On classic apps, remedies use native forms (bin/dev, bin/rails db:migrate, bundle exec rake).
Checks
-
Docker daemon —
docker info --format '{{.ServerVersion}}'Healthy: prints a version. Remedy: start Docker Desktop / OrbStack. -
Containers —
docker compose ps -a --format '{{.Service}}: {{.State}} ({{.Status}})'Healthy:postgres,redis,webrunning (plusworkerandmeilisearchwhen defined in the compose file). Exited app containers are normal if the user just hasn't booted; the remedy isspree dev(foreground, Ctrl+C stops) — orpnpm server:devin monorepo mode. -
Env file — read
.env:SECRET_KEY_BASEpresent and non-empty,SPREE_PORT(default 3000 when absent). NoteSPREE_VERSION_TAGif pinned. Flag a missing.envas the likely root cause for boot loops. -
Web responding —
curl -fsS -o /dev/null -w '%{http_code}' http://localhost:<SPREE_PORT>/(substitute the detected port) Healthy: 2xx/3xx.000= nothing listening (stack down or still booting — checkspree logs);5xx= Rails boot/runtime error (readspree logsand include the first error line in the report).
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.
- 5d ago First seen · 44 lines · 26 tokens per session scan A 95c15af04332
doctor is a command published in the GitHub repository spree/agent-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,037 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create-docker-mcp-tunnel
Stand up an Anthropic MCP tunnel locally with Docker Compose so Claude can call a private MCP server (manual-credentials quickstart).
sandbox
Manage sandbox backends and tooling.
dockerfile
Validate Dockerfiles for GPU/CUDA configuration issues before building.
index
Command "index" from thrashr888/agentkernel, covering commands, quick reference, daily drivers (root level), sandbox lifecycle (sandbox / sb) and ssh (ssh).
deploy
Build, test, deploy with staged rollout.
status
List all SandboxClaims with phase, age, template, and bound pod. Detects stuck-in-Pending claims and surfaces likely causes.