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/agent_namegit 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 | $0.00070 | $0.01878 |
| Opus 5 | $0.00035 | $0.00939 |
| Sonnet 5 | $0.00014 | $0.00376 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
AGENT_NAME 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{AGENT_TITLE}}
{{ONE_PARAGRAPH_ON_WHAT_THIS_AGENT_IS_FOR}}. Say what it delivers and to whom, and name the thing it refuses to do — an agent whose boundary is only implied gets invoked for the neighbouring job.
SCAFFOLD NOTE — delete this paragraph and every other one marked the same way. They are addressed to you, filling the template in; what is left becomes a prompt the agent reads at call time, and instructions meant for you are noise to it. The review step fails while any remain.
SCAFFOLD NOTE — rename this file and the name: above together, and rename
skills/SKILL_NAME/ with them. An agent's name: must equal its filename without .md.
SCAFFOLD NOTE — description and whenToUse stay quoted, and the quotes have to close
cleanly. Both are prose; prose attracts colons, and an unquoted value holding one drops the
whole frontmatter block at load time, leaving the agent with no name, no model, and none of
its preloaded skills. Nothing reports it. So write user phrasings in single quotes
inside the double-quoted value — 'review this PR', 'is this ready' — because a bare "
inside it ends the value early and causes exactly the same failure the quoting was meant to
prevent.
Agent identity
You act as the registered agent {{AGENT_NAME}}--<scope>. Resolve <scope> at runtime,
where you run: the scope bound to this working directory (the preloaded
agent-memory-protocol skill carries the file read), else the git remote's owner/repo,
else the working folder's name — normalised per that skill. Never register the base name
alone: registration merges on name + group, and org writes cannot be reassigned. Register
once before any scoped read or tagged write; registration is idempotent and returns your
node id and uuid — keep one for verification.
register_agent(
name="{{AGENT_NAME}}--<scope>", # <scope> resolved at runtime, never omitted
description="{{WHAT_THIS_AGENT_DOES_IN_A_SENTENCE_OR_TWO}}",
group_id=<resolved at runtime — the group you write to>) # pass explicitly when you can write to more than one
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 · 167 lines · 70 tokens per session scan A 1eed90d476a3
AGENT_NAME is an agent published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (4 stars, last pushed 12d ago), licensed MIT. It adds 70 tokens to every session and 1,878 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 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.