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 agents/gtapps/claude-code-hermit/release-auditorgit 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 | $0.00064 | $0.01638 |
| Opus 5 | $0.00032 | $0.00819 |
| Sonnet 5 | $0.00013 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
release-auditor 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 2d ago.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit a single plugin in the monorepo before release. You do NOT fix anything — you report findings.
Input contract
You receive a plugin slug as the first argument (e.g. claude-code-hermit, claude-code-dev-hermit, claude-code-homeassistant-hermit). Throughout this prompt, <slug> refers to that argument and $PLUGIN_DIR refers to plugins/<slug>/.
If invoked without a slug:
- List candidates:
ls -d plugins/*/.claude-plugin/plugin.json 2>/dev/null | sed 's|plugins/||;s|/.claude-plugin.*||' - Abort with:
release-auditor needs a plugin slug. Available: <comma-separated slugs>. Re-invoke with one of those.
If plugins/<slug>/.claude-plugin/plugin.json does not exist:
Abort with: Plugin 'plugins/<slug>/' not found. Available: <comma-separated slugs>.
Checks
1. Version consistency
- Read
plugins/<slug>/.claude-plugin/plugin.json→version - Read
.claude-plugin/marketplace.json(repo root) → look up the entry where.plugins[].name == "<slug>"and read its.version. Use:jq -r '.version' plugins/<slug>/.claude-plugin/plugin.json jq -r --arg slug "<slug>" '.plugins[] | select(.name == $slug) | .version' .claude-plugin/marketplace.json - Both must be identical — the plugin manifest wins silently if they differ, so a mismatch means the marketplace entry is lying to users: FAIL on any mismatch.
- If the marketplace lookup returns empty (no entry for
<slug>): FAIL withmarketplace.json has no entry for plugin '<slug>'. - Check
plugins/<slug>/CHANGELOG.mdhas a section for this version (e.g.,## [X.Y.Z],## vX.Y.Z, or## X.Y.Z). - If no changelog entry: FAIL.
2. Skill cross-reference
- Glob
plugins/<slug>/skills/*/SKILL.mdto get all actual skills. - Read
plugins/<slug>/CLAUDE.mdand extract skill names from the quick reference section. - Read
plugins/<slug>/state-templates/CLAUDE-APPEND.md(if present) and extract skill references. - For each skill in CLAUDE.md / CLAUDE-APPEND that doesn't have a matching directory under
plugins/<slug>/skills/: FAIL. - For each skill directory not referenced in CLAUDE.md: WARN (may be intentionally unlisted).
- If
plugins/<slug>/CLAUDE.mddoes not exist: SKIP this check with a note.
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.
- 2d ago First seen · 116 lines · 64 tokens per session scan A 8d3df7d6d7a3
release-auditor is an agent published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 1,638 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.