skill-eval-runner
Generic isolated-context runner — executes the analysis spec named in its dispatch and returns the structured output that spec defines. Reusable by any skill (shipped or operator-authored) that needs heavy file reads kept off the main session's inherited context. The calling
$ npx -y skills add gtapps/claude-code-hermit --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Generic isolated-context runner — executes the analysis spec named in its dispatch and returns the structured output that spec defines. Reusable by any skill (shipped or operator-authored) that needs heavy file reads kept off the main session's inherited context. The calling
Agent definition
skill-eval-runner.mdname: skill-eval-runner description: Generic isolated-context runner — executes the analysis spec named in its dispatch and returns the structured output that spec defines. Reusable by any skill (shipped or operator-authored) that needs heavy file reads kept off the main session's inherited context. The calling skill applies any side effects the spec defers to it. effort: medium
You are a generic, isolated-context analysis runner. Your dispatch names an instruction file (a `reference.md` or equivalent spec) and the inputs to use. Read that file and do exactly what it specifies — perform the reads and computations it lists, and return exactly the output it defines, nothing more (no extra prose unless the spec asks for it).
The dispatched spec is the source of truth for what you read, what you return, and what you defer to the caller. Follow its deferral instructions verbatim — when it says "populate this field instead of writing the file" or "return this rather than notifying", do that; the calling skill applies side effects on its own turn. If the spec is silent on whether to act, prefer the read-only option and surface the result in your return value rather than acting on it.
Claude Code plugin that turns a Claude Code instance into a 24/7 agent. Stateful. Proactive. Self-improving through an operator-gated proposal system. Cost-aware. Observable. Works with your Claude Subscription.
Repo: gtapps/claude-code-hermit
Other agents on claude-code-hermit.
- plugin-validator
Validates a single plugin's structure in the monorepo — checks plugin.json consistency, skill frontmatter, hook matcher syntax, template variables, and cross-references between components. Takes a plugin slug. Use after structural changes for fast feedback (release-auditor
Open agent - release-auditor
Pre-release audit for a single plugin in the monorepo — takes a plugin slug and cross-references plugin.json version against the repo-root marketplace.json, CLAUDE.md skill list, hooks.json script paths, state-templates integrity, and CHANGELOG entries. Use before cutting a
Open agent - smoke-test-runner
Runs the contract and hook test suites for a single plugin in the monorepo to validate plugin integrity after changes. Takes a plugin slug. Use before releases or after significant modifications.
Open agent - strava-data-cruncher
Lightweight Haiku subagent for bulk Strava data aggregation — weekly load, zone distribution, efficiency trends. Returns compact structured output; no coaching judgment. Use when you need multi-week trend tables, zone distribution over time, or bulk activity metrics.
Open agent - evolve-runner
Executes the hermit-evolve upgrade (steps 0–9) in an isolated context so the upgrade's transient churn (changelog slice, migration execution, file diffs) never lands in the calling session. Dispatched by the hermit-evolve skill via the Agent tool; returns a compact structured
Open agent - proposal-triage
Pre-creation gate for proposals — deduplicates, cross-references sessions/OPERATOR.md/compiled, and applies the three-condition rule. Accepts one or more candidates in a single call (a single candidate is a batch of one). Returns one verdict per candidate, matched by title:
Open agent