indiestack: Skill for Claude Code

.agents/skills/save-tokens/SKILL.md

save-tokens is a skill for Claude Code from Pattyboi101/indiestack. It costs 24 tokens per session (1,234 once invoked), scanned A, original, MIT.

A project audit that looks for existing tools and services that could replace functionality you are planning to build yourself.

In plain words
What is it for?
Use it while planning or building an application to review its files and dependencies, identify likely replacements, and recommend relevant IndieStack tools.
Why use it?
It helps you spot routine features—such as login, payments, email, forms, analytics, uploads, or monitoring—that may not need custom code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is Pattyboi101/indiestack's own configuration. It tells Claude Code how to work on indiestack itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything indiestack configures →

Part of the indiestack plugin — 4 skills, 6 commands, 1 hook, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Pattyboi101/indiestack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Pattyboi101/indiestack/master/.agents/skills/save-tokens/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Pattyboi101/indiestack

Made for: Claude Code.

Or install indiestack, the plugin that ships this one along with the rest of its 4 skills, 6 commands, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for save-tokens

README.md
[![agentmods](https://agentmods.dev/badge/skills/pattyboi101/indiestack/save-tokens/github.svg)](https://agentmods.dev/skills/pattyboi101/indiestack/save-tokens)
Your own site
<a href="https://agentmods.dev/skills/pattyboi101/indiestack/save-tokens"><img src="https://agentmods.dev/badge/skills/pattyboi101/indiestack/save-tokens/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for save-tokens

Your own site · 80×15
<a href="https://agentmods.dev/skills/pattyboi101/indiestack/save-tokens"><img src="https://agentmods.dev/badge/skills/pattyboi101/indiestack/save-tokens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,234 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.01234
Opus 5 $0.00012 $0.00617
Sonnet 5 $0.00005 $0.00247
Haiku 4.5 $0.00002 $0.00123

Measured 10d ago against content hash a1da0dfbab81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

save-tokens 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 10d 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 -s "https://indiestack.fly.dev/api/tools/search?q=KEYWORD&limit=5"
.agents/skills/save-tokens/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Tokens — IndieStack Workflow Audit

Audit the current project to find indie tools and MCP servers that would save tokens vs building functionality from scratch.

How It Works

You are an efficiency auditor. Developers waste thousands of tokens building common functionality (auth, payments, analytics, email, forms, monitoring) that already exists as polished indie tools. Your job is to identify these opportunities and recommend the best tools from IndieStack.

Step 1: Scan the Project

Look at the current project to understand what's being built:

  1. Read package.json, requirements.txt, pyproject.toml, or Cargo.toml to understand the stack
  2. Scan route files, API handlers, and key source files for patterns:
    • Auth/login flows → could use Clerk, Kinde, Lucia Auth
    • Payment processing → could use LemonSqueezy, Paddle, Polar
    • Analytics/tracking → could use Plausible, Fathom, Simple Analytics
    • Email sending → could use Buttondown, Loops, Resend
    • File uploads → could use Uploadthing, ImageKit
    • Database queries → could use Supabase, Neon, PocketBase
    • Forms → could use Tally, Formbricks
    • Monitoring → could use Better Stack, OpenStatus
    • Browser automation → could use Playwright MCP, Puppeteer MCP
    • Search → could use Brave Search MCP, Exa MCP
  3. Note any TODO, FIXME, or placeholder implementations

Step 2: Search IndieStack

For each opportunity found, query the IndieStack API:

curl -s "https://indiestack.fly.dev/api/tools/search?q=KEYWORD&limit=5"

Also check for MCP servers specifically:

curl -s "https://indiestack.fly.dev/api/tools/search?q=mcp+KEYWORD&limit=3"

And check the tool detail for token estimates:

curl -s "https://indiestack.fly.dev/api/tools/SLUG"

The detail endpoint returns tokens_saved — the estimated tokens you'd spend building this from scratch.

Step 3: Build the Report

Present findings as a structured report:

## Token-Saving Audit Report

### Project: [name]
### Stack: [detected stack]

---

### Opportunities Found

#### 1. [Component Name] — ~XX,000 tokens at risk

**What you're building:** [description of the code/feature]
**What already exists:**

| Tool | Price | Type | Install |
|------|-------|------|---------|
| [Name](indiestack_url) | Free/£X/mo | SaaS/MCP Server | `command` |

**Recommendation:** [Use tool X because...] or [Build this — it's too custom for a generic tool]

---

### Summary

| Component | Tokens at Risk | Recommendation | Tool |
|-----------|---------------|----------------|------|
| Auth      | ~50,000       | Buy            | Clerk |
| Payments  | ~60,000       | Buy            | LemonSqueezy |
| Dashboard | ~30,000       | Build          | Too custom |

**Total tokens saved: ~XXX,000**
**Estimated cost: £XX/mo** (vs writing and maintaining it yourself)

Read the full file on GitHub · 141 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. 10d ago First seen · 141 lines · 24 tokens per session scan A a1da0dfbab81

Subscribe to this mod's changes

save-tokens is a skill published in the GitHub repository Pattyboi101/indiestack (4 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 1,234 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens