tools

A configuration reference for giving software agents access to outside systems and actions. It describes tools for files, web requests, APIs, MCP servers, Python code, and other agents.

In plain words
What is it for?
Use it when configuring an agent to read or write files, call web services, connect to external servers, run Python functions, fetch web pages, or delegate work.
Why use it?
It clarifies which tools an agent can use and how those tools are enabled in a role configuration.

Agent

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/vladkesler/initrunner/tools
Clone the repo
git clone --depth 1 https://github.com/vladkesler/initrunner
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 16,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.16116
Opus 5 $0.00000 $0.08058
Sonnet 5 $0.00000 $0.03223
Haiku 4.5 $0.00000 $0.01612

Measured 2d ago against content hash 9c7b9a7e84d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **No `shell=True`** — Code is executed via `subprocess.run` with list args.
docs/agents/tools.md · 1,557 lines

How it starts

The opening of the file, as written. The whole thing — 1,557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tools — Configuration Reference

Tools give agents the ability to interact with the outside world — reading files, making HTTP requests, connecting to MCP servers, calling APIs, or running custom Python functions. They are configured in the tools list of a role definition. A bare name (- search) enables a tool with defaults; a mapping adds options (- filesystem: {root_path: .}).

In addition to explicitly configured tools, InitRunner auto-registers tools when ingest or memory sections are present in the role definition. Any unrecognized tool name is routed to the plugin registry.

Tool Types

Type Description
filesystem Read/write files within a sandboxed root directory
http Make HTTP requests to a base URL
mcp Connect to MCP servers (stdio, SSE, streamable-http)
custom Load Python functions from a module — single function or auto-discover all
delegate Invoke other agents as tool calls (inline or remote)
api Declarative REST API endpoints defined entirely in YAML
web_reader Fetch web pages and convert to markdown
python Execute Python code in a subprocess with isolation
datetime Get current time and parse dates
sql Query SQLite databases with read-only pragma
git Run git operations in a subprocess with read-only default
shell Execute commands in a subprocess with allow/block lists
slack Send messages to Slack via incoming webhooks
web_scraper Fetch, chunk, embed, and store web pages in the document store
search Search the web and news via DuckDuckGo, SerpAPI, Brave, or Tavily
audio Fetch YouTube transcripts and transcribe local audio files
csv_analysis Inspect, summarize, and query CSV files within a sandboxed directory
think Internal reasoning scratchpad — agent thinks step-by-step without user-visible output
clarify Agent-initiated mid-run clarification — pauses execution to ask the user a question
script Inline shell scripts defined in YAML as named, parameterized tools
calculator Safe mathematical expression evaluator (AST-based, no eval)
pdf_extract Extract text and metadata from PDF files inline
image_gen Generate images via OpenAI DALL-E or Stability AI
mcp (browser) Browser automation via agent-browser MCP server
(plugin) Any other type is resolved via the plugin registry

Read the full file on GitHub · 1,557 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 · 1,557 lines · 0 tokens per session scan A 9c7b9a7e84d3

Subscribe to this mod's changes

tools is an agent published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 16,116 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.