blocks-develop

A development workflow for creating TPMJS registry tools with the blocks command-line tool. It covers describing a tool, creating its package, implementing it with the AI SDK, checking it, and publishing it to npm.

In plain words
What is it for?
Use it to define tool inputs and outputs, build the package files, validate the implementation, and publish a TPMJS tool.
Why use it?
It gives developers the required structure and checks needed for a tool to pass validation and be published.

Command for Claude Code

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 commands/tpmjs/tpmjs/blocks-develop
Clone the repo
git clone --depth 1 https://github.com/tpmjs/tpmjs

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 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 $0.00010 $0.00737
Opus 5 $0.00005 $0.00368
Sonnet 5 $0.00002 $0.00147
Haiku 4.5 $0.00001 $0.00074

Measured 2d ago against content hash dc15ce64fbbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blocks-develop 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://tpmjs.com/api/sync/keyword -H "Authorization: Bearer $CRON_SECRET"
.claude/commands/blocks-develop.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Help the user develop new tools for the TPMJS registry using the blocks CLI. This workflow covers defining tools in blocks.yml, implementing them with AI SDK v6, validating with the blocks CLI, and publishing to npm.

Development Workflow

1. Define Tool in blocks.yml

Add tool definition to packages/tools/official/blocks.yml:

blocks:
  category.toolName:
    type: utility
    description: "Clear description for LLMs"
    path: "tool-directory-name"
    domain_rules:
      - id: rule_name
        description: "Implementation requirement"
    inputs:
      - name: paramName
        type: string
        description: "Parameter description"
    outputs:
      - name: result
        type: ResultType
        description: "Output description"
        measures: [working_implementation, valid_output_structure, proper_error_handling, ai_sdk_compliance]

2. Create Package Structure

packages/tools/official/tool-name/
├── package.json      # npm package with tpmjs field
├── tsconfig.json     # Extends @tpmjs/tsconfig
├── tsup.config.ts    # Build config
├── block.ts          # REQUIRED by validator
├── index.ts          # Re-export from src
└── src/index.ts      # Main implementation

3. Implement with AI SDK v6

import { jsonSchema, tool } from 'ai';

export const myTool = tool({
  description: 'Description for LLMs',
  parameters: jsonSchema<InputType>({
    type: 'object',
    properties: { /* ... */ },
    required: ['field1'],
  }),
  async execute(input): Promise<OutputType> {
    // REAL implementation - no stubs
    return result;
  },
});

export default myTool;

4. Run Validation

cd packages/tools/official
pnpm blocks run tool-name          # Validate single tool
pnpm blocks run tool-name --force  # Force full validation
pnpm blocks run --all              # Validate all tools

5. Build and Publish

pnpm build
npm publish --access public

# Trigger sync to tpmjs.com
source apps/web/.env.local
curl -X POST https://tpmjs.com/api/sync/keyword -H "Authorization: Bearer $CRON_SECRET"

Read the full file on GitHub · 103 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 · 103 lines · 10 tokens per session scan A dc15ce64fbbe

Subscribe to this mod's changes

blocks-develop is a command published in the GitHub repository tpmjs/tpmjs (24 stars, last pushed 8d ago), licensed MIT. It adds 10 tokens to every session and 737 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.