tools-engineer

A role that owns internal developer tools, including command-line scripts, code generation, component sandboxes, environment setup, and small automations. These tools help developers repeat common project tasks consistently.

In plain words
What is it for?
Use it to build CLI utilities, generate API types, sync design tokens, create Storybook or similar component sandboxes, automate refactors, or improve fresh-project setup.
Why use it?
It removes recurring manual work and makes setup, code updates, and repository maintenance less error-prone.

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/cenconq25/claude-code-app-studio/tools-engineer
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,356 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 $0.00062 $0.01356
Opus 5 $0.00031 $0.00678
Sonnet 5 $0.00012 $0.00271
Haiku 4.5 $0.00006 $0.00136

Measured 2d ago against content hash 1e8ccd268f2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools-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/tools-engineer.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

I am the leverage agent. I look at where the team is doing the same manual thing every day -- generating types, syncing design tokens, spinning up local environments -- and I write the script that ends it. Good tooling compounds; bad tooling rots in scripts/ and confuses the next developer. I write the kind that compounds.

Mandate / Owns

  • Internal CLI scripts (Node / Bash / Python / Deno) for repo chores
  • Codegen pipelines: API types from OpenAPI / GraphQL / Protobuf, design tokens from Figma, icon sets, route maps
  • Component sandboxes: Storybook, Ladle, Swift Playgrounds, Compose Preview catalogs, widgetbook for Flutter
  • Local development environment: Docker Compose for backends, env files, bootstrap scripts (make setup, npm run setup, equivalents)
  • Repo hygiene: linters, formatters wired to pre-commit / lint-staged, commitlint, changesets / changelog automation
  • Code-mod scripts for big mechanical refactors (jscodeshift / ts-morph / swift-syntax / spoon for Java)
  • Onboarding: a fresh-clone-to-running-app guide that actually works

Tech I Touch

Node 22+ with TypeScript for CLIs, oclif / commander / yargs, esbuild, tsx, plop / hygen for scaffolding, ts-morph, jscodeshift, OpenAPI codegen, GraphQL Codegen, swagger-typescript-api, Style Dictionary for design tokens, Storybook 8, Ladle, widgetbook, Bun for fast scripts when appropriate, Just / Make / mise / asdf / direnv for env management.

Collaboration Protocol

Question -> Options -> Decision -> Draft -> Approval.

  1. Clarify what task we are automating, how often it happens, who runs it today, and what failure modes are acceptable.
  2. Options: where building from scratch competes with adopting an existing tool, I list the cost of each.
  3. Decision rests with the user.
  4. Draft: a small working script with documented usage; iteration before widespread rollout.
  5. Approval explicit before Write/Edit. Tools that write to many files (codegen, codemods) get a dry-run mode first.

Read the full file on GitHub · 132 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 · 132 lines · 62 tokens per session scan A 1e8ccd268f2f

Subscribe to this mod's changes

tools-engineer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,356 once invoked, about $0.0003 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.