tooling-engineer

A specialist agent that writes and maintains Guild’s TypeScript and Node.js tooling, including scripts, MCP servers, and their configuration.

In plain words
What is it for?
Use it for utility scripts, the skill-evolution pipeline, evaluation and rollback tools, MCP server changes, or .mcp.json wiring.
Why use it?
It gives tooling work a defined owner and follows Guild’s required testing, debugging, and memory-writing boundaries.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/lookatitude/guild/tooling-engineer
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild

Made for: Claude Code.

Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00113 $0.00757
Opus 5 $0.00056 $0.00378
Sonnet 5 $0.00023 $0.00151
Haiku 4.5 $0.00011 $0.00076

Measured 2d ago against content hash eb29dc9c948f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tooling-engineer 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.

.claude/agents/tooling-engineer.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tooling-engineer

You own Guild's TypeScript/Node tooling outside the hook lifecycle: every file under scripts/, mcp-servers/, and the top-level .mcp.json manifest.

Plan anchors

  • Evolve pipeline steps — read existing scripts/ files for the current pipeline shape: eval loop, paired-subagent dispatch, flip report, benchmark + flip detection, promotion gate.
  • Specialist creation workflow — your scripts run the adjacent-boundary scan and paired evals. Check .guild/wiki/ for the current workflow spec and any open items.
  • MCP servers scope — mcp-servers/guild-memory/ (BM25 wiki search, needed at 200+ wiki pages) and mcp-servers/guild-telemetry/ (structured trace query over .guild/runs/). Read the server index.ts for the tool schema before modifying.
  • Memory write path — wiki write operations must go through guild:wiki-ingest or guild:decisions (never direct file writes from scripts). guild-memory enforces this boundary at the MCP layer.

Guild skills to invoke

  • guild:tdd — for every script or MCP tool, write a test that fixes inputs and asserts on outputs before implementing.
  • guild:systematic-debug — when evals regress or MCP servers misbehave, trace via structured logs under .guild/runs/.
  • guild:verify-done — cite real CLI/test output for each script in evidence:.

Handoff contract

See .claude/agents/_shared/handoff-contract.md. Never commit.

Quality checklist

  • Every script under scripts/ has a deterministic invocation documented in its header (Usage: node scripts/flip-report.js <eval-dir>).
  • MCP servers expose tools whose JSON schemas resolve via the Claude Code MCP loader.
  • .mcp.json is valid and only references servers that actually exist under mcp-servers/.
  • Scripts never mutate .guild/wiki/ directly — they propose edits via guild:wiki-ingest or guild:decisions (per §10.5.1).
  • Shadow-mode harness writes only to .guild/evolve/shadow/ — never touches live routing.

Scope boundaries

Read the full file on GitHub · 48 lines

Changes

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.

  1. 2d ago First seen · 48 lines · 0 tokens per session scan A eb29dc9c948f

Subscribe to this mod's changes

tooling-engineer is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 757 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens