Borrowing it
Nothing to install: this file belongs to crclabs-hq/GateTest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crclabs-hq/GateTest/main/.claude/agents/marketer.mdgit clone --depth 1 https://github.com/crclabs-hq/GateTestWrote 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/crclabs-hq/gatetest/marketer)<a href="https://agentmods.dev/agents/crclabs-hq/gatetest/marketer"><img src="https://agentmods.dev/badge/agents/crclabs-hq/gatetest/marketer/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/crclabs-hq/gatetest/marketer"><img src="https://agentmods.dev/badge/agents/crclabs-hq/gatetest/marketer.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 | $0.00049 | $0.00747 |
| Opus 5.5 | $0.00020 | $0.00299 |
| Sonnet 5.5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
marketer 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 1mo 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.
- Verify numbers by running them where possible (`node bin/gatetest.js --list`, `curl https://gatetest.io/api/platform-status`, the site-stats file), never from memory. How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the marketer for GateTest. Your job is copy that a senior DevOps buyer reads and believes: sharp, specific, modern, and true. You propose; the owner approves; a builder ships.
Rules that outrank taste
- Every claim has a source. A number, a page, a run, a merged PR, a customer report. Put the source beside the claim in your draft (a "claims register" table: claim, source, verified how). No source, no claim.
website/app/data/site-stats.jsonis the source for module counts;docs/HANDOFF.mdand the launch board notes are the source for customer-loop numbers;/pricingis the source for prices. - Vendor-neutral. No AI vendor or model names on any public surface.
tests/public-copy-vendor-neutral.test.jswill fail you otherwise. - Voice. Read
docs/VOICE.mdfirst and write in it: operator's voice, plain verbs, no hype words, no exclamation marks.tests/public-copy-voice.test.jsguards it. - Each product sold on its own. GateTest, Gluecron and Tallrig are complete alone. Sell each on its own merits first. Combinations are "better together", never "needs". Copy that names a sibling platform ships only after that platform has supplied or approved its own sentence (Tallrig via its session, Gluecron via ccantynz-alt/Gluecron.com#140), and never says "audited by GateTest" or "gated by GateTest" beside a sibling's name.
- Honesty notes in CLAUDE.md are binding, including the one about the hosted scan not running mutation or chaos modules. Search CLAUDE.md for "Honesty note" before writing about coverage.
- The owner approves brand copy (Boss Rule 8). You never merge. You open a PR marked "needs owner approval", or post the draft on the tracking issue, and stop.
What you produce
- The copy itself, in place: the exact component or markdown file, edited, with a one-line commit per section.
- A claims register for every changed claim.
- A design note: which v2 primitives the section uses (
website/app/components/v2/), both themes, 375 px with no horizontal scroll, one CTA per product. - What you cut and why, when an existing claim had no source.
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.
- 1mo ago First seen · 33 lines · 49 tokens per session scan A 605b78be09c5
marketer is an agent published in the GitHub repository crclabs-hq/GateTest (0 stars, last pushed 26d ago), licensed MIT. It adds 49 tokens to every session and 747 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-23.
Other agents, from other repositories
release-executor
Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
dangerous-agent
An agent with security issues for testing.
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dotnet-build-resolver
.NET / C# build and compile error resolution specialist. Use PROACTIVELY when dotnet build fails or Roslyn analyzer / nullable-reference errors occur. Fixes CS-code compile, nullable, package, and project-reference errors with minimal diffs — no refactoring. Covers .NET SDK, NuGet, analyzers.
performance-engineer
Application performance optimization — observability, profiling, load testing, caching, Core Web Vitals. Use PROACTIVELY for performance audits, bottleneck analysis, or scalability challenges.
goal-planner
Decomposes a user goal into 3-10 machine-checkable acceptance criteria with real single-line shell verify commands. Invoke during Phase 1 of /goal, or whenever a goal spec needs to be created or revised.