hermit-routines

hermit-routines is a skill for Claude Code from gtapps/claude-code-hermit. It costs 36 tokens per session (5,043 once invoked), scanned A, original, MIT.

A scheduling skill for registering and managing recurring routines through one persistent background monitor when available, with scheduled jobs as a fallback.

In plain words
What is it for?
Use it to load, reset, or run scheduled routines, including the heartbeat restart routine.
Why use it?
It keeps routine checks registered and restores them when monitoring becomes stale or unavailable.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-code-hermit plugin — 30 skills, 4 agents shipped together

Good fit Use it to load, reset, or run scheduled routines, including the heartbeat restart routine.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add gtapps/claude-code-hermit
Claude Code
/plugin install claude-code-hermit

Made for: Claude Code.

Or install claude-code-hermit, the plugin that ships this one along with the rest of its 30 skills, 4 agents.

Wrote 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.

agentmods badge for hermit-routines

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/hermit-routines.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/hermit-routines)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/hermit-routines"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/hermit-routines.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,043 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.05043
Opus 5 $0.00018 $0.02521
Sonnet 5 $0.00007 $0.01009
Haiku 4.5 $0.00004 $0.00504

Measured today against content hash b1a9d00f707d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hermit-routines 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 today.

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.

plugins/claude-code-hermit/skills/hermit-routines/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Routines

Register and manage scheduled routines. Where the Monitor tool is available, all enabled routines except heartbeat-restart run from ONE persistent Monitor subprocess that decides eligibility outside the session — a skipped fire costs zero model tokens. heartbeat-restart stays a CronCreate re-arm anchor: its skill IS load, so its daily fire re-arms the monitor and the anchor CronCreate — and, unless heartbeat.enabled is explicitly false, restores the heartbeat monitor too. The watchdog re-arms a monitor whose liveness has gone stale as a second net, on a resting session too. Where Monitor is unavailable (Bedrock/Google Cloud Agent Platform/Foundry, DISABLE_TELEMETRY/CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC), load falls back to per-routine CronCreates.

Usage

/claude-code-hermit:hermit-routines load              register/reconcile: monitor mode if available, else CronCreate diff-register
/claude-code-hermit:hermit-routines load --reset      unconditional reset: tear down + recreate everything
/claude-code-hermit:hermit-routines run <ids>          [internal] ROUTINE_DUE handler — invoked by the monitor's notification
/claude-code-hermit:hermit-routines list               list configured routines from config.json
/claude-code-hermit:hermit-routines status              show monitor/anchor state (or CronCreate registrations in fallback mode)
/claude-code-hermit:hermit-routines stop [id]           stop the monitor (or a specific fallback-mode CronCreate)
/claude-code-hermit:hermit-routines stop --all          stop everything

list, status, stop and the notes live in reference.md, beside this file in the skill's Base directoryRead it for those. load and run stay here: every always-on launch pays for them.

Plan

load

Called automatically by hermit-start.ts on always-on launches. Can also be called manually to apply config changes mid-session.

  1. Resolve the plugin root path: derive it from this skill's Base directory, which the harness injects into the invocation context as <plugin_root>/skills/hermit-routines. Strip the trailing /skills/hermit-routines to get pluginRoot. This works in both installed and --plugin-dir modes. ($CLAUDE_PLUGIN_ROOT is NOT a Bash env var at runtime — evaluating it in Bash always returns empty. The braced ${CLAUDE_PLUGIN_ROOT} form is text-substituted in skill markdown only in installed mode. Neither is reliable here — always use the Base-directory derivation.) The resolved pluginRoot must be baked into the Monitor command and into any CronCreate-delivered prompt at registration — it is not available inside either subprocess or cron-delivered prompts.

Read the full file on GitHub · 119 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. today Changed · +2 lines b1a9d00f707d
  2. yesterday Changed 0cb77292ab56
  3. 2d ago Changed · +3 lines 7ef638b4fd7d
  4. 4d ago Changed · -51 lines fd9e4abcf204
  5. 6d ago Changed · +14 lines 607521898cfe
  6. 8d ago First seen · 151 lines · 36 tokens per session scan A 80bd89f3e98c

Subscribe to this mod's changes

hermit-routines is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 5,043 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.