A development workflow for defining and registering an AI assistant tool in a TypeScript codebase. It combines supported capabilities, optional plugins, marketplace settings, content rewriting, and build rules.

Use it to create or change a tool definition, add plugin support, implement reversible content rewrites, register and test the tool, and declare its framework build behavior.

It provides a defined path for adding a tool while keeping its type requirements, registration, rewriting behavior, plugins, and build configuration consistent.

tool — Skill by ai-driven-dev

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 skills/ai-driven-dev/framework/tool

Any agent

npx skills add ai-driven-dev/framework --skill tool

Clone the repo

git clone --depth 1 https://github.com/ai-driven-dev/framework

Made for: Claude Code, Codex.

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 917 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00121	$0.00917
Opus 5	$0.00060	$0.00458
Sonnet 5	$0.00024	$0.00183
Haiku 4.5	$0.00012	$0.00092

Measured 2d ago against content hash 83aa89fb6efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool 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 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.

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.

cli/.claude/skills/tool/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool

Builds a complete AI tool definition: a typed object implementing AiTool<C> where C is an intersection of Has* interfaces sourced from domain/tools/contracts.ts, registered via registerTool, and optionally equipped with PluginsCapability and marketplaceSettings.

Available actions

#	Action	Role	Input
01	`define-toolconfig`	Compose the AiTool object from Has* capabilities	tool name + required capabilities list
02	`content-rewrite`	Implement lossless rewriteContent / reverseRewriteContent	tool file from 01
03	`plugins-and-marketplace`	Configure PluginsCapability + marketplaceSettings	tool file from 01
04	`register-and-test`	Call registerTool and validate the full definition	completed tool from 01-03
05	`build-contract`	Declare the tool's `framework build` behavior via `ToolBuildContract`	tool from 01 + modes (marketplace/flat)

Default flow

01 → 02 → 03 → 04 then 05 when the tool must be an aidd framework build target.

Skip 03 when the tool has no plugin capability. Skip 02 when the tool reuses base rewrite helpers without modification (document this explicitly). Skip 05 when the tool is not a framework-build target.

Transversal rules

Tool file lives in domain/tools/ai/<tool-name>.ts; one file per tool.
AiTool<C> where C is an intersection of Has* interfaces — never a plain object literal without the type annotation.
Capability presence guard uses "agents" in tool.capabilities (in-check), not instanceof.
rewriteContent and reverseRewriteContent must be exact inverses; compose baseRewriteContent/baseReverseRewriteContent first, then apply tool-specific transforms.
signalDir points to the directory scanned for name: aidd: signals; required and non-null for AI tools.
directory is the root output directory for the tool (e.g. .acme/).
Call registerTool(config) at module bottom — never from use-cases or application layer.
Named export only; no default export.
.js extensions on all relative imports.
No any types.
Framework-build behavior is declared by ONE artifact-symmetric ToolBuildContract (all six artifact kinds: skills/agents/mcp/hooks/rules/commands), consumed by the two per-mode orchestrators — NEVER a per-tool *OutputStrategy class, NEVER a per-tool/per-artifact branch in an orchestrator. Unsupported kinds are { supported: false } (warn-and-skip).
Build contracts reuse existing path/transform/merge helpers; generalize a helper rather than reimplement it. Flat MCP merges key-prefix servers by <plugin>-.

Read the full file on GitHub · 62 lines

Files

What ships with it

10 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.

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.

2d ago First seen · 62 lines · 121 tokens per session scan A 83aa89fb6efe

Subscribe to this mod's changes

tool is a skill published in the GitHub repository ai-driven-dev/framework (445 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 917 once invoked, about $0.0006 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.

Languages Testing Writing and docs agent agentic ai ai-driven-development commands context-engineering

smoke-test

End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…

bytedance/deer-flow · 0 tokens

image-generation

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

bytedance/deer-flow · 42 tokens

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens

vercel-deploy

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

bytedance/deer-flow · 69 tokens

zeroclaw

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…

zeroclaw-labs/zeroclaw · 167 tokens

github-issue-triage

Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…

zeroclaw-labs/zeroclaw · 140 tokens