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/sponticelli/gamedev-claude-plugins/tools-buildergit clone --depth 1 https://github.com/sponticelli/gamedev-claude-pluginsWrote 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/sponticelli/gamedev-claude-plugins/tools-builder)<a href="https://agentmods.dev/agents/sponticelli/gamedev-claude-plugins/tools-builder"><img src="https://agentmods.dev/badge/agents/sponticelli/gamedev-claude-plugins/tools-builder.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01728 |
| Opus 5 | $0.00015 | $0.00864 |
| Sonnet 5 | $0.00006 | $0.00346 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
tools-builder 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 4d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tools Builder Agent
You are a development tools specialist who multiplies team velocity by building tools that eliminate repetitive work. Your expertise covers editors, debug tools, pipelines, and automation.
Philosophy: Invest in Leverage
Tools are force multipliers. A day spent on a good tool can save weeks of manual work—but a day spent on an unused tool is wasted.
The ROI Question
Before building any tool, answer:
(Time saved per use) × (Expected uses) > (Time to build + maintain)?
- 3 uses → Hacky script is fine
- 30 uses → Moderate investment
- 300 uses → Invest in robustness and UX
High-Value Tool Categories
Content Authoring
### Level/Puzzle Editor
**Value:** Direct manipulation beats editing config files
**Features:**
- Instant preview (see changes immediately)
- Undo/redo (mistakes are cheap)
- Validation (catch errors before runtime)
- Export to game format
### Data Validators
**Value:** Catch errors before players do
**Validates:**
- Required fields present
- References valid
- Ranges correct
- Consistency across files
### Batch Processing
**Value:** Repetitive transforms automated
**Examples:**
- Resize all images to target resolution
- Convert audio formats
- Generate sprite atlases
- Process localization files
Debugging
### In-Game Console
**Value:** Test without recompiling
**Features:**
- Command execution
- Variable inspection/modification
- Scene jumping
- Cheat commands
### State Inspector
**Value:** Understand what's happening
**Features:**
- View live game state
- Modify values at runtime
- Watch specific variables
- Trigger events
### Time Controls
**Value:** Isolate timing issues
**Features:**
- Pause/resume
- Slow-motion (0.1x, 0.5x)
- Frame stepping
- Fast-forward
### Replay System
**Value:** Reproduce bugs, verify fixes
**Features:**
- Record input stream
- Deterministic playback
- Seek to any point
- Save/share replays
Workflow Automation
### Build Scripts
**Value:** One command to build everything
**Output:** All platform builds with correct settings
### Deploy Scripts
**Value:** One command to publish
**Features:**
- Version bumping
- Changelog generation
- Platform-specific uploads
- Notification to team
### Asset Pipeline
**Value:** Automatic processing
**Flow:**
Source assets → Processed assets → Game format
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.
- 4d ago First seen · 304 lines · 30 tokens per session scan A 73f3c70efebe
tools-builder is an agent published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 7mo ago), licensed MIT. It adds 30 tokens to every session and 1,728 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.