starter-author

starter-author is an agent for Claude Code from CassetteTapeCrackle/claude-starters. It costs 50 tokens per session (472 once invoked), scanned A, original, MIT.

An agent for creating starter templates that give a programming language or technology stack its project rules, commands, and tests.

In plain words
What is it for?
Use it to scaffold a starter with build, dependency, coding, testing, and command guidance, plus a manifest and content checks.
Why use it?
It avoids inventing a new structure each time and keeps starters consistent with the existing claude-starters repository.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the claude-starters plugin — 9 skills, 1 command, 8 agents, 2 hooks shipped together

Good fit Use it to scaffold a starter with build, dependency, coding, testing, and command guidance, plus a manifest and content checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cassettetapecrackle/claude-starters/starter-author
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.

Clone the repo
git clone --depth 1 https://github.com/CassetteTapeCrackle/claude-starters

Made for: Claude Code.

Or install claude-starters, the plugin that ships this one along with the rest of its 9 skills, 1 command, 8 agents, 2 hooks.

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 starter-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/cassettetapecrackle/claude-starters/starter-author/github.svg)](https://agentmods.dev/agents/cassettetapecrackle/claude-starters/starter-author)
Your own site
<a href="https://agentmods.dev/agents/cassettetapecrackle/claude-starters/starter-author"><img src="https://agentmods.dev/badge/agents/cassettetapecrackle/claude-starters/starter-author/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 starter-author

Your own site · 80×15
<a href="https://agentmods.dev/agents/cassettetapecrackle/claude-starters/starter-author"><img src="https://agentmods.dev/badge/agents/cassettetapecrackle/claude-starters/starter-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.00472
Opus 5 $0.00025 $0.00236
Sonnet 5 $0.00010 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 10d ago against content hash 77fc3adab9cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

starter-author 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 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.

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.

agents/starter-author.md · 23 lines

What it actually says

You author new starters for the ~/claude-starters repo. Work TDD and keep everything lean.

Method

  1. Read an existing starter as a pattern (e.g. starters/rust/ or starters/cpp/) and starters/<x>/manifest.json. Match structure and tone.
  2. Create starters/<stack>/CLAUDE.md:
    • First line after the title: Framework: __FRAMEWORK__ — locked. ... (the __FRAMEWORK__ token is substituted at apply time — keep it verbatim).
    • Sections: Build & deps · Code · Tests · (Depth, if a matching clean-code-<x> skill exists — name it explicitly) · Commands.
    • Rules must be the language's canonical conventions (formatter, linter, test runner, error-handling norm). Greppable names, one responsibility, early returns. No line-count dogma.
  3. Create starters/<stack>/manifest.json: stack, frameworks (array), optional skill, and a commands map (test/lint/format/etc.).
  4. Add assertions to tests/blind-starters-content.test.sh (or a stack test) covering a signature token + valid manifest.
  5. If the language needs deeper, on-demand rules, create skills/clean-code-<x>/SKILL.md (frontmatter name + trigger description, lean body) — the plugin auto-discovers skills/.

Principles

  • The project CLAUDE.md is always in context — keep it tight; put depth in the on-demand skill, not here.
  • Run the full suite (for t in tests/*.test.sh; do bash "$t"; done) and shellcheck before reporting done.
  • Report a concise summary: files added, what the rules cover, test result.
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 · 23 lines · 50 tokens per session scan A 77fc3adab9cf

Subscribe to this mod's changes

starter-author is an agent published in the GitHub repository CassetteTapeCrackle/claude-starters (1 stars, last pushed 21d ago), licensed MIT. It adds 50 tokens to every session and 472 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories

fable-lens

Blind adversarial reviewer dispatched by fable-review — attacks a real artifact through one named lens and returns findings. Read-only by capability, not by request: it holds no Edit/Write/Bash and cannot dispatch further subagents. Not for general work; the dispatcher supplies the lens and the scope.

debabsah/fable-method · 65 tokens

horizon

Use for large, multi-feature goals that benefit from durable planning, delegated implementation, autonomous decisions, retry-bounded evaluation, and a final audit.

Master0fFate/parallax-claudecode · 32 tokens

parallax

Use proactively for non-trivial implementation, refactoring, and debugging that needs explicit invariants, gated writes, verification, and an auditable trace.

Master0fFate/parallax-claudecode · 33 tokens

horizon-auditor

Independently audits one completed Horizon worker attempt against its acceptance criteria and observed receipt. Use only after Horizon observes the worker receipt.

Master0fFate/parallax-claudecode · 32 tokens

horizon-worker

Implements exactly one Horizon feature and returns a bounded evidence handoff. Use only when dispatched by the Horizon supervisor.

Master0fFate/parallax-claudecode · 27 tokens

product-ideation-market-researcher

Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.

QBall-Inc/the-bulwark · 64 tokens