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/commitnpx skills add gtapps/claude-code-hermit --skill commitgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWhat 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 | $0.00104 | $0.01295 |
| Opus 5 | $0.00052 | $0.00647 |
| Sonnet 5 | $0.00021 | $0.00259 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
commit 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 yesterday.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Detect which plugin's scope this change belongs to, append a changelog line in that plugin's CHANGELOG, then commit. No push, no tag, no version bump — that's /release's job.
Guardrails (check before starting)
- Clean tree (
git statusshows nothing) → stop and say so, nothing to commit. - Detached HEAD, mid-rebase, or mid-merge → stop and ask the user to resolve that first.
- Never
--amend,--no-verify, force-push, or create tags here. - Never use
git add -Aorgit add .— staging is path-scoped per step 0. - If a pre-commit hook fails, fix the root cause and create a new commit — don't bypass the hook.
mainis the default base for everyday work. Claude Code's/plugin updateonly fires whenversioninplugin.jsonchanges, so commits merged tomainbetween releases are invisible to operators on the standard install path —[Unreleased]accumulates until/releaseships them.
Steps
0. Detect scope
Run git status --porcelain and partition the changed paths:
- Paths matching
plugins/<X>/...→ group by<X>(the slug). - Paths outside
plugins/(root README,.github/,.claude/,.claude-plugin/marketplace.json, root configs) → "root-scope" paths.
Then decide:
- Single plugin slug, no root-scope paths → set
$PLUGIN_DIR = plugins/<slug>/, set$SCOPE = plugin. Continue. - Multiple plugin slugs touched → stop. Print the per-slug file groups and ask the user to split the change into separate
/commitruns (one per plugin). Do not stage anything. - Single plugin slug + a few root-scope paths → ask the user via AskUserQuestion: "Bundle the root-scope files (
<list>) into the<slug>commit, or split them out as a separate root-scope commit?" Default to splitting if uncertain. - Root-scope only (no
plugins/<X>/...) → set$SCOPE = root,$PLUGIN_DIR = none. Continue.
The rest of this skill branches on $SCOPE.
1. Review the diff
Run git status and git diff HEAD (or git diff if nothing staged yet). Scan for:
- Secrets or credentials (
.env, API keys, tokens) - Large binaries or generated files that shouldn't be versioned
- Unrelated files that shouldn't be bundled in this commit
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.
- yesterday First seen · 79 lines · 104 tokens per session scan A 08e22a8c3cd8
commit is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 1,295 once invoked, about $0.0005 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.