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 commands/bankrbot/claude-plugins/scaffoldgit clone --depth 1 https://github.com/BankrBot/claude-pluginsWrote 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/commands/bankrbot/claude-plugins/scaffold)<a href="https://agentmods.dev/commands/bankrbot/claude-plugins/scaffold"><img src="https://agentmods.dev/badge/commands/bankrbot/claude-plugins/scaffold.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00012 | $0.00703 |
| Opus 5 | $0.00006 | $0.00351 |
| Sonnet 5 | $0.00002 | $0.00141 |
| Haiku 4.5 | $0.00001 | $0.00070 |
Grade A, and why
scaffold 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bankr Project Scaffold
Create a complete TypeScript/Node.js project scaffold for building on the Bankr Agent API.
Process
-
Determine project type - If
$ARGUMENTSspecifies a type, use it. Otherwise, ask the user.Load the
bankr-project-templatesskill for available types:- bot - Automated trading bot, price monitor, alert system, scheduled task
- web-service - HTTP API that wraps or extends Bankr functionality
- dashboard - Web UI for portfolio tracking, market analysis, monitoring
- cli - Command-line tool for Bankr operations
-
Ask for project details:
- Project name (kebab-case, e.g.,
my-trading-bot) - Brief description of what it will do
- Any specific Bankr operations it will use (trading, prices, polymarket, defi)
- Package manager preference: bun (recommended - faster) or npm
- Project name (kebab-case, e.g.,
-
Create project structure:
- Load
bankr-project-templatesskill for the directory structure - Load
bankr-client-patternsskill for common files and client code - Create all directories using
mkdir -p - Write each file using the Write tool
- Customize based on user's description
- Load
-
Explain next steps:
- How to get a Bankr API key (https://bankr.bot/api)
- How to run the project (use selected package manager:
bun install && bun devornpm install && npm run dev) - What to customize first based on their use case
Skills to Load
Core Skills (always load):
bankr-project-templates- Directory structures for each project typebankr-client-patterns- bankr-client.ts and common files (package.json, tsconfig.json, .env.example, .gitignore)bankr-api-basics- API documentation for reference
Capability Skills (load based on project purpose):
bankr-token-trading- For trading bots: prompt templates, swap response handlingbankr-transfers- For payment bots: recipient resolution, transfer patternsbankr-polymarket- For prediction market bots: betting API, position trackingbankr-leverage-trading- For leverage bots: Avantis patterns, position managementbankr-nft-operations- For NFT bots: OpenSea browsing, purchase automationbankr-portfolio- For dashboards: balance aggregation, portfolio trackingbankr-market-research- For price bots: monitoring patterns, alert systemsbankr-automation- For order bots: limit orders, DCA, TWAP implementationbankr-token-deployment- For token launchers: Clanker integration, fee claiming
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.
- 4d ago First seen · 63 lines · 12 tokens per session scan A e822dc3ce312
scaffold is a command published in the GitHub repository BankrBot/claude-plugins (83 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 703 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.