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/hermit-settingsnpx skills add gtapps/claude-code-hermit --skill hermit-settingsgit 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/hermit-settings)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/hermit-settings"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/hermit-settings.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 | $0.00041 | $0.10775 |
| Opus 5 | $0.00020 | $0.05387 |
| Sonnet 5 | $0.00008 | $0.02155 |
| Haiku 4.5 | $0.00004 | $0.01077 |
Grade A, and why
hermit-settings 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.
How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermit Settings
View or modify the hermit configuration for this project.
Step 0 — Channel reply
If this skill was invoked from a channel-arrived message (the inbound prompt contains a <channel source="..."> tag), reply via that channel's reply tool. Otherwise emit to conversation.
Security tier — authority depends on which chat asks. Settings that decide what this hermit may do, or who may talk to it, are tiered (docs/security.md § Tiered settings authority):
The settings chat below means the chat configured as maintainer_channel_id — or, on an operator-run install (operator_profile: technical) that never configured one, the hermit's own home chat. A configured maintainer chat turns that fallback off rather than widening it.
- Settings chat only —
remote,escalation,docker,artifact-backend, and anything not named below. Changeable from the settings chat (allowlist-checked), or from a terminal. From any other chat: view-only. - Settings chat, plus a confirmation code on an
askchannel —permissions(permission mode),env,monitors(each entry carries a shell command),boot-skill(standing instructions re-applied at every restart),shutdown_skill(its counterpart, invoked on every full close) andvoice.prose(free text that becomes every future session's system prompt; the style name is everyday-tier). On a channel whosesettings_policyisallowthese apply from the settings chat like the tier above, no code. Onask, the gate issues a short code and denies the write: send the settings chat a message that names the exact change and carries the code, then stop — a bare code asks the operator to approve something they can't see. Quote the change exactly as the gate showed it: a value rendered[set]or[cleared]is withheld deliberately and stays that way. It applies only after the operator echoes the code back from that same chat. Don't retry the setting in the same turn. - Terminal only, from every chat including the settings one —
allowed_users,briefing_chat, the DM chat,maintainer_channel_iditself,settings_policyitself,operator_profile,settings_permissions, and any channel operation that replaces a channel wholesale (add/remove/primary). Show the current value, say plainly it changes only from a terminal session with/claude-code-hermit:hermit-settings <argument>, and change nothing. - Switched off for that channel — when its
settings_policyisdeny, every tier above the everyday settings is terminal-only there, the settings chat included. Say so plainly and name the terminal command.
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.
- today Changed · -6 lines 2d54769b5505
- today Changed ac1af518f4a6
- yesterday Changed · +2 lines 70655c8fac51
- 4d ago First seen · 437 lines · 41 tokens per session scan A 5ed8d2e6ceff
hermit-settings is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 10,775 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
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.