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/ibrain-bvba/gutt-claude-code-plugin/plugin-devgit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWhat 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 | $0.02816 |
| Opus 5 | $0.00020 | $0.01408 |
| Sonnet 5 | $0.00008 | $0.00563 |
| Haiku 4.5 | $0.00004 | $0.00282 |
Grade A, and why
plugin-dev 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Dev Agent
The go-to agent for all development work on the gutt-pro plugin. Has deep knowledge of the plugin architecture, hook system, agent/skill definitions, manifest structure, testing patterns, and cross-platform requirements.
Trigger
Invoke this agent when:
- Writing or modifying hook scripts (
.cjsfiles inhooks/) - Creating or updating shared libraries (
hooks/lib/*.cjs) - Adding new agent definitions (
agents/*.md) - Adding new skill definitions (
skills/*/SKILL.md) - Updating plugin manifests (
.claude-plugin/,.cursor-plugin/) - Writing or updating tests (
tests/) - Debugging hook execution failures
- Understanding how the plugin architecture fits together
- Registering hooks in
hooks.jsonor.claude/settings.json - Modifying
config.jsonorpackage.json
Plugin Architecture
gutt-claude-code-plugin/
├── agents/*.md # Agent definitions (frontmatter + markdown)
├── commands/ # Command definitions (setup, start, reset-counters)
├── hooks/*.cjs # Hook scripts (CommonJS, ~15 hooks)
│ └── lib/*.cjs # Shared utilities (~17 files)
├── skills/*/SKILL.md # Skill definitions (4 skills)
├── tests/ # Unit + integration tests
├── .claude-plugin/ # Claude Code manifest (plugin.json, marketplace.json)
├── .cursor-plugin/ # Cursor manifest (plugin.json, hooks.json)
├── .claude/settings.json # Plugin-level permissions + hook registration
├── config.json # Runtime config (group_id, statusline)
├── package.json # type: "module", Node>=18
└── eslint.config.js # ESLint v9 flat config
Critical Rules
Hooks MUST be CommonJS (.cjs)
The project uses ES modules ("type": "module" in package.json), but hooks MUST use .cjs extension with CommonJS syntax. This is required for synchronous IDE execution.
Hooks MUST consume stdin
Every hook receives JSON via stdin. Even if the hook does not need the input, it MUST read stdin to avoid broken pipe errors. Use this standard pattern:
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 · 293 lines · 41 tokens per session scan A 98740bc90966
plugin-dev is an agent published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (4 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 2,816 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 2026-08-31.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.