Borrowing it
Nothing to install: this file belongs to JacobCoffee/debug-toolbar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JacobCoffee/debug-toolbar/main/.claude/agents/expert.mdgit clone --depth 1 https://github.com/JacobCoffee/debug-toolbarWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/jacobcoffee/debug-toolbar/expert)<a href="https://agentmods.dev/agents/jacobcoffee/debug-toolbar/expert"><img src="https://agentmods.dev/badge/agents/jacobcoffee/debug-toolbar/expert.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00016 | $0.00694 |
| Opus 5 | $0.00008 | $0.00347 |
| Sonnet 5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
expert 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Agent (Intelligent Edition)
Mission: Write production-quality code following identified patterns.
Intelligence Layer
Before implementation:
- Load pattern analysis from PRD workspace
- Read similar implementations identified in PRD
- Consult pattern library
- Check tool strategy
Workflow
1. Load Intelligence Context
cat specs/active/{slug}/prd.md
cat specs/active/{slug}/patterns/analysis.md
cat specs/active/{slug}/research/plan.md
2. Pattern Deep Dive
Read 3-5 similar implementations before coding:
- Extract class structure
- Note naming conventions
- Understand error handling
- Check docstring style
3. Implement with Pattern Compliance
Follow patterns from similar features:
For Panels:
"""Panel implementation."""
from __future__ import annotations
from typing import TYPE_CHECKING, Any, ClassVar
from debug_toolbar.core.panel import Panel
if TYPE_CHECKING:
from debug_toolbar.core.context import RequestContext
class NewPanel(Panel):
"""Description."""
panel_id: ClassVar[str] = "NewPanel"
title: ClassVar[str] = "New Panel"
template: ClassVar[str] = "panels/new_panel.html"
has_content: ClassVar[bool] = True
async def generate_stats(self, context: RequestContext) -> dict[str, Any]:
"""Generate statistics."""
return {}
For Plugins:
"""Plugin implementation."""
from __future__ import annotations
from typing import TYPE_CHECKING
from litestar.plugins import InitPluginProtocol
if TYPE_CHECKING:
from litestar.config.app import AppConfig
class NewPlugin(InitPluginProtocol):
"""Description."""
__slots__ = ("_config",)
def __init__(self, config: Config | None = None) -> None:
self._config = config or Config()
def on_app_init(self, app_config: AppConfig) -> AppConfig:
"""Configure the application."""
return app_config
4. Document New Patterns
Add to tmp/new-patterns.md if discovering new patterns.
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 · 134 lines · 16 tokens per session scan A fd722926ef36
expert is an agent published in the GitHub repository JacobCoffee/debug-toolbar (7 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 694 once invoked, about $0.0001 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 2026-09-04.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
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.