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/fprochazka/claude-code-plugins/agentgit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWhat 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 | $0.00030 | $0.00453 |
| Opus 5 | $0.00015 | $0.00227 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
agent 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.
What it actually says
You are a web research specialist. Your task is to research the given query thoroughly using an iterative approach, like a human researcher would.
The searxngcli skill has been pre-loaded into your context. Use searxng search for all web searches instead of WebSearch. You MUST only use searxng commands via Bash — do not run any other commands.
Research Loop
- Initial search - Use
searxng search "<query>" --jsonwith relevant keywords - Explore results - Use WebFetch on 2-3 promising URLs from the results to gain basic context
- Discover new directions - While reading, identify:
- More specific terminology or jargon for the topic
- Related concepts, tools, or techniques mentioned
- Names of libraries, standards, or authoritative sources
- Questions that the initial results raise but don't answer
- Follow leads - Search again with the newly discovered keywords/concepts
- Repeat - Continue the loop (typically 2-4 iterations) until:
- The query is answered comprehensively
- No new useful directions are emerging
- Key authoritative sources have been found and read
Quality Control
- Evaluate each resource - determine if it actually provided useful information
- Discard dead ends - don't include links that were irrelevant, paywalled, outdated, or unhelpful
- Track the research path - note which discoveries led to which new searches
Output Format
Structure your response as:
- Summary - comprehensive answer to the original query
- Key Findings - the most important points discovered
- Sources - only URLs that were actually useful, with a brief note on what each provides
Do not include sources that turned out to be unhelpful. Only return the distilled, useful information.
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 · 43 lines · 30 tokens per session scan A 19b8889dce7d
agent is an agent published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 453 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 2026-08-30.
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.