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 gtapps/claude-code-hermit/plugin install laravel-forge-hermitWrote 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/gtapps/claude-code-hermit/forge-servers)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/forge-servers"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/forge-servers.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 5.1 | $0.00057 | $0.00982 |
| Opus 5 | $0.00028 | $0.00491 |
| Sonnet 5 | $0.00011 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
forge-servers 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Servers
List and inspect servers in the Forge estate, or reboot a server with approval.
List all servers
php ${CLAUDE_PLUGIN_ROOT}/php/forge.php servers
Output: one line per server with ID, name, and IP address.
Show server detail
php ${CLAUDE_PLUGIN_ROOT}/php/forge.php server <server>
<server> can be a server name, IP address, or numeric ID. Ambiguous names are rejected with a list of collisions.
Reboot a server (surface-then-approve)
Step 1 — Preview (read-only, no action taken):
php ${CLAUDE_PLUGIN_ROOT}/php/forge.php preview-reboot <server>
Resolves <server> to the canonical record and prints the server name, IP, and ID. Exit 0, no mutation.
Step 2 — Relay to operator. Show the canonical target. Ask for explicit approval.
Step 3 — On approval only:
php ${CLAUDE_PLUGIN_ROOT}/php/forge.php server-reboot <server> --confirm
A wrong reboot causes an outage. Never auto-confirm. Never skip the preview step.
Monitors
Monitors have no curated command — they use the generic write path, which is how every SDK write other than deploy and server-reboot works.
List what exists:
echo '[<server-id>]' | php ${CLAUDE_PLUGIN_ROOT}/php/forge.php call monitors
Step 1 — Preview. Captures the exact HTTP request without sending it and stores it as a single-use plan:
echo '[<server-id>, {"type":"cpu_load","operator":"gte","threshold":90,"notify":"[email protected]"}]' \
| php ${CLAUDE_PLUGIN_ROOT}/php/forge.php preview createMonitor
Prints the canonical server, POST /orgs/<org>/servers/<id>/monitors, the payload, and a plan id.
Step 2 — Relay and wait. Send the canonical server and the payload to the operator and ask for approval. Nothing has been sent to Forge at this point.
Step 3 — On approval only:
php ${CLAUDE_PLUGIN_ROOT}/php/forge.php execute <plan-id>
Plans are single use and expire 15 minutes after the preview. If approval arrives later, the plan is gone — re-run the preview and relay the new one. Do not treat that as an error to work around: it is the mechanism refusing to fire something the operator did not just look at.
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.
- 2d ago First seen · 97 lines · 57 tokens per session scan A ae7487dccee8
forge-servers is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 982 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
sre-bot
Answer questions about production health and investigate incidents using live Kubernetes and observability data. Invoke whenever someone asks whether something is broken, slow, erroring, or down; asks what happened during an outage or time window; asks about alerts, logs, metrics, traces, or error rates; asks why a…
ccc-deploy
CC Commander actual deployment workflow. Detects Vercel, Fly.io, Cloudflare, GitHub Pages, or npm deploy targets, asks for the deploy destination, runs the platform…
terraform-expert
Use when working with .tf/.tofu/.tfvars files, HCL, terraform or tofu CLI commands, providers, modules, remote state/backends, tfstate, or plan/apply pipelines. Writes and refactors Terraform 1.9+/OpenTofu configurations, designs reusable modules, performs safe state surgery, and wires CI plan/apply workflows. Invoke…
ship
Ship (optional) — deploy the CLOSED build and prove it in prod — deploy via the repo's own path, re-run reconciliation on prod data, confirm the observability signal emits. Skipped if the contract marks deploy out of scope. Trigger after compass:review-build closes, or on "ship it", "deploy", "compass ship".
ccc-pro-observability
OpenTelemetry, Honeycomb, Datadog, and structured logging wiring · Pro tier only.
id-architect
The read-only forward-design ENTRY mode (infra-delivery step 2) — for "the app runs locally, there is NO deployment yet — design where it should run." Design a target infra topology from requirements (archetype × load projection × cost/ops/compliance → selected stack-profile(s)), then run the adversarial DESIGN-AUDIT…