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 skills add fortunto2/solo-factory --skill agent-tool-designgit clone --depth 1 https://github.com/fortunto2/solo-factoryWrote 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/skills/fortunto2/solo-factory/agent-tool-design)<a href="https://agentmods.dev/skills/fortunto2/solo-factory/agent-tool-design"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/agent-tool-design/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/skills/fortunto2/solo-factory/agent-tool-design"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/agent-tool-design.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 | $0.00042 | $0.03172 |
| Opus 5 | $0.00021 | $0.01586 |
| Sonnet 5 | $0.00008 | $0.00634 |
| Haiku 4.5 | $0.00004 | $0.00317 |
Grade A, and why
agent-tool-design 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 10d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Design Principles for AI Agents
Practical guide to designing tool systems for LLM-powered agents, distilled from building a PAC1 benchmark agent (Rust, 16 tools reduced to 12, tested across 7 models, 40+ tasks) and studying Codex CLI and Claude Code architectures.
See references/ for code patterns, comparison tables, and a quick checklist.
1. Tool Count Sweet Spot
Every tool in the schema is a token cost and a new failure mode. Models degrade on long tool lists.
Industry reference points:
| Agent | Core | Extended/Deferred | Total in Schema |
|---|---|---|---|
| Claude Code | 7 | 33 (deferred via ToolSearch) | 7-40 |
| Codex CLI | 7 | 0 | 7 |
| mini-SWE-agent | 1 (bash) | 0 | 1 |
| PAC1 agent | 14 | 8 deferred | 14 active + 8 deferred |
| SGR Python | 3-6 + reasoning | 0 | Union schema (structured output) |
See references/comparison.md for full architecture comparison.
Rules:
- Start with 7 core tools. Add only when you can measure round-trip savings.
- Track tool usage rate per task. Remove tools with <5% usage across benchmark.
- Every tool added must justify itself: "saves N round-trips per task" or "prevents failure mode X."
- Test with your weakest target model first -- if it can't handle the tool count, the design is wrong.
Anti-pattern: Adding a tool "just in case." We added mkdir, move_file, find -- usage was <3%. Disabled them. Zero regression.
2. Three-Tier Organization
CORE (always in schema)
Universal agent capabilities: observe (read, search, list, tree), act (write, delete, eval), report (answer, context).
Codex CLI uses exactly 7: shell, apply_patch, read_file, list_dir, grep_files, search_bm25, js_repl. Our PAC1 agent uses 9 core tools. Both converge on the same categories.
EXTENDED (batch operations)
Justified only when saving 3+ round-trips per task. Example: read_all saved 44 round-trips on our hardest task (48 to 4 tool calls).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 295 lines · 42 tokens per session scan A 902040408330
agent-tool-design is a skill published in the GitHub repository fortunto2/solo-factory (18 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 3,172 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 skills, from other repositories
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
together-ai-inference
Serverless inference, fine-tuning, embeddings, image generation, and batch processing on 200+ open-source models via an OpenAI-compatible API. Use when you need fast, cost-effective access to open-source LLMs without managing infrastructure.
phone-harness
Control the user's phone — iPhone through the Mac's iPhone Mirroring window, or an Android over adb: open apps, tap, type, swipe, read the screen.
angular-modern-apis
Guidelines for using modern Angular APIs (signals, inject, control flow).
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.
skillgrade-setup
Sets up and runs skillgrade evaluation pipelines for Agent Skills. Use when initializing eval configurations, running trials, reviewing results, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.