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.
git clone --depth 1 https://github.com/CassetteTapeCrackle/claude-startersWrote 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/agents/cassettetapecrackle/claude-starters/naming-agent)<a href="https://agentmods.dev/agents/cassettetapecrackle/claude-starters/naming-agent"><img src="https://agentmods.dev/badge/agents/cassettetapecrackle/claude-starters/naming-agent/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.
<a href="https://agentmods.dev/agents/cassettetapecrackle/claude-starters/naming-agent"><img src="https://agentmods.dev/badge/agents/cassettetapecrackle/claude-starters/naming-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.00237 |
| Opus 5 | $0.00021 | $0.00118 |
| Sonnet 5 | $0.00008 | $0.00047 |
| Haiku 4.5 | $0.00004 | $0.00024 |
Grade A, and why
naming-agent 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.
What it actually says
You produce names that are memorable and practical.
Method
- Clarify what's being named and the constraints: tone (playful/pro), length, audience, and whether it's a product name or a code identifier.
- Generate candidates across a few directions (descriptive, evocative, metaphor, coined). For each: a one-line rationale.
- Practical checks:
- Product: rough availability signal (domain/handle/existing product with the name), pronounceability, no unfortunate meanings.
- Code: distinctive and greppable (grep returns few false hits), not a generic term (
data/manager), consistent with existing naming.
- Recommend a top pick and a runner-up, with why.
Output
- A shortlist with rationale + checks, and a clear recommendation. Flag any name with a clash or availability risk.
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.
- 10d ago First seen · 19 lines · 42 tokens per session scan A 3a78038c1244
naming-agent is an agent published in the GitHub repository CassetteTapeCrackle/claude-starters (1 stars, last pushed 21d ago), licensed MIT. It adds 42 tokens to every session and 237 once invoked, about $0.0002 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.
Other agents, from other repositories
creo-image-generation
Subagent for generating marketing images using DALL-E 3 or ComfyUI (Stable Diffusion XL). Handles batch generation, cost estimation, SEO image creation, and image optimization.
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.
horizon
Use for large, multi-feature goals that benefit from durable planning, delegated implementation, autonomous decisions, retry-bounded evaluation, and a final audit.
parallax
Use proactively for non-trivial implementation, refactoring, and debugging that needs explicit invariants, gated writes, verification, and an auditable trace.
horizon-auditor
Independently audits one completed Horizon worker attempt against its acceptance criteria and observed receipt. Use only after Horizon observes the worker receipt.
horizon-worker
Implements exactly one Horizon feature and returns a bounded evidence handoff. Use only when dispatched by the Horizon supervisor.