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/managedcode/dotpilot/agent-toolsgit clone --depth 1 https://github.com/managedcode/dotPilotWhat 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 | $0.00008 | $0.02119 |
| Opus 5 | $0.00004 | $0.01059 |
| Sonnet 5 | $0.00002 | $0.00424 |
| Haiku 4.5 | $0.00001 | $0.00212 |
Grade A, and why
agent-tools 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 yesterday.
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.
This is a copy
95% identical to agent-tools — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Tools
Tooling support can vary considerably between different agent types. Some agents might allow developers to customize the agent at construction time by providing external function tools or by choosing to activate specific built-in tools that are supported by the agent. On the other hand, some custom agents might support no customization via providing external or activating built-in tools, if they already provide defined features that shouldn't be changed.
::: zone pivot="programming-language-csharp"
Therefore, the base abstraction does not provide any direct tooling support, however each agent can choose whether it accepts tooling customization at construction time.
Tooling support with ChatClientAgent
The ChatClientAgent is an agent class that can be used to build agentic capabilities on top of any inference service. It comes with support for:
- Using your own function tools with the agent
- Using built-in tools that the underlying service might support.
[!TIP] For more information on
ChatClientAgentand information on supported services, see Simple agents based on inference services
Provide AIFunction instances during agent construction
There are various ways to construct a ChatClientAgent, for example, directly or via factory helper methods on various service clients, but all support passing tools.
// Sample function tool.
[Description("Get the weather for a given location.")]
static string GetWeather([Description("The location to get the weather for.")] string location)
=> $"The weather in {location} is cloudy with a high of 15°C.";
// When calling the ChatClientAgent constructor.
new ChatClientAgent(
chatClient,
instructions: "You are a helpful assistant",
tools: [AIFunctionFactory.Create(GetWeather)]);
// When using one of the helper factory methods.
openAIResponseClient.AsAIAgent(
instructions: "You are a helpful assistant",
tools: [AIFunctionFactory.Create(GetWeather)]);
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.
- yesterday First seen · 296 lines · 8 tokens per session scan A 8a452d3f720b
agent-tools is an agent published in the GitHub repository managedcode/dotPilot (23 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 2,119 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to agent-tools, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
Explore
Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
Transcribe
Batch audio/video transcription to SRT. Wraps /skill:video-transcription. Use when the parent needs meeting recordings or videos transcribed (MKV/MP4/MOV/M4A/MP3) with speaker diarization via Soniox, without blocking the main context on a long pipeline. Returns output paths + a short summary.
tool_creation
This guide covers the four ways to extend InitRunner with tools: built-in tools (contributing to InitRunner itself), custom tools (Python modules), declarative API tools (YAML-only), and the plugin registry (distributable packages).
registry
InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to /.initrunner/roles/ where they integrate automatically with the CLI.