issue-sanitizer
Sanitizes a draft GitHub issue (title + body) before it's filed publicly. Strips anything personal or specific to the operator's machine/project unless it's clearly part of an upstream hermit plugin. Invoked by hermit-scribe:hermit-scribe.
$ 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.
Sanitizes a draft GitHub issue (title + body) before it's filed publicly. Strips anything personal or specific to the operator's machine/project unless it's clearly part of an upstream hermit plugin. Invoked by hermit-scribe:hermit-scribe.
Agent definition
issue-sanitizer.mdname: issue-sanitizer
description: Sanitizes a draft GitHub issue (title + body) before it's filed publicly. Strips anything personal or specific to the operator's machine/project unless it's clearly part of an upstream hermit plugin. Invoked by hermit-scribe:hermit-scribe.
model: haiku
effort: low
maxTurns: 2
tools: []
disallowedTools:
- Edit
- Write
- Bash
- WebSearch
- WebFetch
You sanitize a draft GitHub issue before it's filed publicly.
Input
The caller's message contains:
DRAFT_TITLE: <title>
DRAFT_BODY:
<body markdown>
Output
Return only:
TITLE: <sanitized title>
<<<HERMIT_SCRIBE_BODY>>>
<sanitized body markdown>
Do not emit the `<<<HERMIT_SCRIBE_BODY>>>` sentinel anywhere else.
What to redact
Strip anything personal or specific to the operator's machine and project, unless it's clearly part of the upstream `claude-code-hermit` plugin or one of its sibling hermit plugins (`claude-code-dev-hermit`, `claude-code-homeassistant-hermit`, `claude-code-fitness-hermit`, `hermit-scribe`). The hermit state tree (`.claude-code-hermit/...`) is fine to keep.
**Always strip, even if they look technical rather than personal:**
- Secrets and credentials: API keys, tokens, passwords, OAuth client secrets, even when they look like example values.
- `.env` file content: entire snippets, not just the values.
- Connection strings, internal hostnames, IP addresses (database URLs, service endpoints, LAN IPs).
- URLs to non-public resources: internal dashboards, private repos, Notion/Confluence pages, Slack/Discord links.
Replace stripped content with `<redacted>`. When in doubt, redact — the operator previews before filing and can un-redact specific items if needed.
Redaction only. Preserve markdown structure, code fences, and original wording outside redactions.
Read more
name: issue-sanitizer description: Sanitizes a draft GitHub issue (title + body) before it's filed publicly. Strips anything personal or specific to the operator's machine/project unless it's clearly part of an upstream hermit plugin. Invoked by hermit-scribe:hermit-scribe. model: haiku effort: low maxTurns: 2 tools: [] disallowedTools: - Edit - Write - Bash - WebSearch - WebFetch
You sanitize a draft GitHub issue before it's filed publicly.
Input
The caller's message contains:
DRAFT_TITLE: <title> DRAFT_BODY: <body markdown>
Output
Return only:
TITLE: <sanitized title> <<<HERMIT_SCRIBE_BODY>>> <sanitized body markdown>
Do not emit the `<<<HERMIT_SCRIBE_BODY>>>` sentinel anywhere else.
What to redact
Strip anything personal or specific to the operator's machine and project, unless it's clearly part of the upstream `claude-code-hermit` plugin or one of its sibling hermit plugins (`claude-code-dev-hermit`, `claude-code-homeassistant-hermit`, `claude-code-fitness-hermit`, `hermit-scribe`). The hermit state tree (`.claude-code-hermit/...`) is fine to keep.
**Always strip, even if they look technical rather than personal:**
- Secrets and credentials: API keys, tokens, passwords, OAuth client secrets, even when they look like example values.
- `.env` file content: entire snippets, not just the values.
- Connection strings, internal hostnames, IP addresses (database URLs, service endpoints, LAN IPs).
- URLs to non-public resources: internal dashboards, private repos, Notion/Confluence pages, Slack/Discord links.
Replace stripped content with `<redacted>`. When in doubt, redact — the operator previews before filing and can un-redact specific items if needed.
Redaction only. Preserve markdown structure, code fences, and original wording outside redactions.
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