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 simbajigege/book2skills --skill agent-tool-buildergit clone --depth 1 https://github.com/simbajigege/book2skillsWrote 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/simbajigege/book2skills/agent-tool-builder)<a href="https://agentmods.dev/skills/simbajigege/book2skills/agent-tool-builder"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/agent-tool-builder/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/simbajigege/book2skills/agent-tool-builder"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/agent-tool-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00104 | $0.01998 |
| Opus 5 | $0.00052 | $0.00999 |
| Sonnet 5 | $0.00021 | $0.00400 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade A, and why
agent-tool-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 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Tool Builder
Helps define agent tools using the fail-closed design pattern: a unified class that co-locates identity, schema, security properties, and execution logic, with fail-closed defaults so new tools are safe by default.
Why this pattern matters
Three things that ad-hoc tool definitions lack:
- Fail-closed defaults —
is_read_only,is_destructive,is_concurrency_safeall default to False. A tool that forgets to declare its properties is conservatively treated as write-capable. - Layered execution —
validate_semantics → check_permissions → _callare separate methods, so validation logic doesn't bleed into permission logic or business logic. - Self-contained definition — schema, description, security metadata, and execution all live in one place. No separate middleware to wire up.
Workflow
Step 1 — Identify the target framework
Ask which agent framework the tool will be registered in (e.g. hermes-agent, LangChain, plain Python). This determines the import path and registration method, but the design principles are identical.
Check if agent_tool_base.py exists in the project's utils/tools directory.
If not, copy it from references/agent_tool_base.py in this skill directory.
Tell the user where it was placed.
Step 2 — Interview the user
Collect answers to these questions. Defaults are shown — skip questions where the default is clearly fine.
Naming convention: use {service}_{action}_{resource} format with a service prefix so the tool stays unambiguous when multiple tool sets are loaded simultaneously (e.g. stock_get_price, stock_list_symbols, stock_search_news). Start with a verb: get, list, search, create, delete.
| Field | Question | Default |
|---|---|---|
name |
工具名（格式：{service}_{action}_{resource}，例如 stock_get_price） |
— required |
description |
给 LLM 看的一句话描述：精确匹配实际功能，不要模糊扩大，否则 agent 会在不该用的场景误调用 | — required |
| Schema fields | 工具接受哪些参数？（字段名、类型、说明；在 Field description 里加 example） | — required |
is_read_only |
这个工具只读数据，不写入/不产生副作用吗？ | False |
is_destructive |
这个工具会做不可逆操作（删除、覆盖）吗？ | False |
is_concurrency_safe |
这个工具可以和其他工具同时运行吗？ | False |
response_format |
返回数据是给 agent 程序化处理（JSON）还是给用户展示（Markdown）？ | 视场景，默认 Markdown |
| 是否列表工具 | 如果返回多条记录，要支持分页吗？ | 超过 50 条建议加 |
_validate_input_semantics |
有没有需要在执行前拦截的语义问题？（如：参数太短、格式不对） | 不需要 |
_check_permissions |
有没有需要检查的权限？（如：需要某个 env var、调用方身份限制） | 不需要 |
_call |
工具的核心执行逻辑是什么？ | — required |
What ships with it
3 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 · 204 lines · 104 tokens per session scan A 65e39fc47093
agent-tool-builder is a skill published in the GitHub repository simbajigege/book2skills (162 stars, last pushed 15d ago), licensed MIT. It adds 104 tokens to every session and 1,998 once invoked, about $0.0005 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
marketing-strategy-pmm
Product marketing, positioning, GTM strategy, and competitive intelligence. Includes ICP definition, April Dunford positioning methodology, launch playbooks, competitive battlecards, and international market entry guides. Use when developing positioning, planning product launches, creating messaging, analyzing…
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention.…
email-sequence
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.