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 skills/gtapps/claude-code-hermit/rc-gatenpx skills add gtapps/claude-code-hermit --skill rc-gategit clone --depth 1 https://github.com/gtapps/claude-code-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/rc-gate)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/rc-gate"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/rc-gate.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 | $0.00038 | $0.00608 |
| Opus 5 | $0.00019 | $0.00304 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
rc-gate 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 4d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RC Gate
The spawn gate is a claude remote-control server the hermit runs as its own
tmux child. While it is open, the operator can spawn new sessions into this
project from claude.ai/code or the mobile app; each spawn lands in its own git
worktree, so this folder stays single-session and the hermit keeps its own state.
This is a different leg from config.remote, which makes the hermit itself
reachable. Both can be on; neither implies the other.
Verbs
All four are .claude-code-hermit/bin/hermit-run rc-server <verb>:
| Verb | What it does | Output |
|---|---|---|
start |
opens the gate (tmux session hermit-rc-gate), waits for the server |
ready <url> or a one-line refusal |
status |
one pane read | down, starting (up but not serving yet), ready, or connected N/32; a second spawns: N live (<names>) line when spawn worktrees exist |
stop |
closes the gate, then sweeps | closed / down, plus any removals |
gc |
sweeps worktrees left by archived spawns | one line per worktree removed, or kept because it holds uncommitted work |
start prints the claude.ai/code?environment=… URL — that is what the operator
opens or scans. Hand it over as a link, not as a command.
Run each verb bare. The grant for these four is an exact command match, so a
pipe, a redirect, or a timeout/cd wrapper falls outside it and re-prompts.
Behavior
Report state, not mechanics — whether the operator can spawn from their phone, and the link if so. Never the tmux session name, the flags, or the pane text.
A spawned session is visible only to the claude.ai account signed in here, and the server refuses to start without that login. Anyone with access to that account can spawn while the gate is open.
When start refuses with the not-logged-in verdict, that is final. Say it once,
don't retry, don't propose workarounds.
Leftover worktrees are swept automatically while the routine monitor runs. Run
gc for an on-demand sweep that reports kept; stop already sweeps. A kept
line means that worktree holds uncommitted work: say it is there and let the
operator decide, never delete it for them.
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.
- 4d ago First seen · 49 lines · 38 tokens per session scan A 4863fdbe0f18
rc-gate is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 608 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…