Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/agents/tool-names.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/tool-names)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/tool-names"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/tool-names/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/tool-names"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/tool-names.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.03569 |
| Opus 5.5 | $0.00012 | $0.01428 |
| Sonnet 5.5 | $0.00006 | $0.00714 |
| Haiku 4.5 | $0.00003 | $0.00357 |
Grade A, and why
tool-names 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Names - Add Missing Friendly Names
Resolve issues that report unknown/missing tool display names by adding entries to src/toolNames.json. This agent understands MCP (Model Context Protocol) server naming conventions and can research tool origins.
When to Use This Agent
Trigger this agent when:
- An issue reports unknown or missing friendly tool names (title like "Add missing friendly names for tools")
- New MCP tools appear in user session logs without display labels
- The sync-toolnames workflow detects new upstream tools from
microsoft/vscode-copilot-chat
Key Files
src/toolNames.json — The single mapping file from raw tool identifiers to human-readable display names. Every tool the extension encounters gets looked up here; missing entries show as "Unknown" in the UI.
src/automaticTools.json — An array of tool IDs that Copilot calls automatically on its own (file reads, directory listings, searches, error checks, confirmations, memory, etc.). These tools are excluded from fluency scoring because they don't reflect intentional user configuration. When adding new tool entries to toolNames.json, you must also decide whether each tool is automatic or intentional and add it to automaticTools.json if automatic.
MCP Tool Name Conventions
MCP tools follow predictable naming patterns. The raw tool identifier encodes the MCP server origin and the action:
Prefix Patterns (raw identifier → display prefix)
| Raw Prefix | Display Prefix | Source Repository |
|---|---|---|
mcp.io.github.git. or mcp_io_github_git_ |
GitHub MCP (Local): |
github/github-mcp-server |
mcp_github_github_ |
GitHub MCP (Remote): |
github/github-mcp-server |
mcp_github-code-s_ |
GitHub MCP (Code Scanning): |
github/github-mcp-server |
mcp_com_microsoft_ |
Microsoft MCP: |
Microsoft internal MCP server |
mcp_microsoftdocs_microsoft_ |
Microsoft Docs MCP: |
Microsoft MCP server for official documentation retrieval |
mcp_gitkraken_ |
GitKraken MCP: |
GitKraken (no public MCP server repo; tools come from the GitKraken VS Code extension) |
mcp_oraios_serena_ |
Serena: |
oraios/serena |
mcp_microsoft_pla_ |
Playwright MCP: |
microsoft/playwright-mcp |
mcp_io_github_ups_ |
Context7 MCP: |
upstash/context7 |
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 · 199 lines · 30 tokens per session scan A b2f39ddafcf1
tool-names is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 3,569 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.
Other agents, from other repositories
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.
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.