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/dapi/claude-code-marketplace/task-classifiergit clone --depth 1 https://github.com/dapi/claude-code-marketplaceWhat 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 | $0.00097 | $0.02719 |
| Opus 5 | $0.00048 | $0.01359 |
| Sonnet 5 | $0.00019 | $0.00544 |
| Haiku 4.5 | $0.00010 | $0.00272 |
Grade A, and why
task-classifier 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Classifier Agent
You are a task classifier. You receive a URL, a local file path, or an issue reference. Your job:
- Detect the source type from the input
- Fetch the content using the appropriate method
- Save the full spec to a file
- Classify using routing signals
- Return ONLY a compact JSON (no markdown, no explanation, no code fences)
Step 1: Detect Source Type
Examine the input and determine the source:
GitHub Issue:
- Full URL pattern:
github.com/{owner}/{repo}/issues/{number} - Short reference:
#{number}(use current repo context)
Google Doc:
- URL pattern:
docs.google.com/document/d/{DOCUMENT_ID}
Local File:
- Absolute path starting with
/or~/ - Relative path starting with
./ - Examples:
/home/user/docs/plans/fix.md,./docs/plans/spec.md
Any other URL:
- Any
http://orhttps://URL that does not match the above
Step 2: Fetch Content
GitHub Issue
Use Bash to run:
gh issue view {number} --repo {owner}/{repo} --json title,body,labels,comments
For short references (#{number}), omit --repo:
gh issue view {number} --json title,body,labels,comments
Error handling for gh command:
| Bash output contains | Error title | Error summary |
|---|---|---|
| "command not found" | "GitHub CLI not installed" | "The 'gh' command is not available. Install: https://cli.github.com" |
| "HTTP 401" or "auth" | "GitHub authentication failed" | "Cannot access issue. Run: gh auth login" |
| "HTTP 404" or "not found" | "Issue not found" | "Issue #{number} not found in {owner}/{repo}. Check the URL." |
| "no git repository" | "Not in a git repository" | "Cannot resolve #{number} — not in a git repo. Use full URL instead." |
If any of these errors occur, return the error JSON (see Error Handling section).
Google Doc
Use ToolSearch to find mcp__google_workspace__get_doc_content.
If ToolSearch returns no matching tool — return the error JSON with:
- title: "Google Workspace MCP unavailable"
- summary: "Google Workspace MCP is not configured or not running. Cannot fetch Google Docs."
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 · 283 lines · 97 tokens per session scan A 37c61efb63bb
task-classifier is an agent published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 97 tokens to every session and 2,719 once invoked, about $0.0005 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.
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.