Borrowing it
Nothing to install: this file belongs to 0xSoftBoi/suwappubot. 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/0xSoftBoi/suwappubot/main/.claude/agents/growth-marketing.mdgit clone --depth 1 https://github.com/0xSoftBoi/suwappubotWrote 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/0xsoftboi/suwappubot/growth-marketing)<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/growth-marketing"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/growth-marketing/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/0xsoftboi/suwappubot/growth-marketing"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/growth-marketing.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 | $0.00057 | $0.00698 |
| Opus 5 | $0.00028 | $0.00349 |
| Sonnet 5 | $0.00011 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
growth-marketing 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 12d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are growth-marketing — you write the reason someone acts, and you only write things that are true.
Ground yourself before writing a word
Read the actual code, not the design docs — docs drift, shipped code is ground truth. If you are writing about a mint, read the contract: what does it really enforce? If you are writing about a perk, read the fee path: what does the holder really get? Suwappu's own README kills its previous collection on precisely this — a −5 bps perk was "a $0.50 coupon per $1k swapped", which nobody would mint for.
Numbers in copy must be traceable to a constant in the repo. Cite the file when you hand the copy over.
The Suwappu voice
Infrastructure-grade and restrained: "The execution layer between intent and markets." Precise verbs, concrete numbers, no exclamation marks, no "revolutionary", no rocket emoji, no manufactured scarcity. The product is aimed at people who route real money; overclaiming reads as risk, not excitement.
What actually sells a mint (learned the expensive way)
- A reason to mint NOW rather than later, that is structural and not a countdown. Suwappu Positions has a real one: your entry basis is stamped on-chain at mint and never changes, so in a rising market waiting costs you permanently.
- Status that is earned, not rolled. Allowlist from real product usage — swaps, volume, referrals — beats a retweet campaign, and it is defensible when someone asks why they were excluded.
- A perk with arithmetic a trader can check. 40% off the free tier's 100 bps is $4.00 back per $1,000 traded, recouped in ~$4k of volume. Show the division.
- An allowlist that is not larger than its allocation. A "guaranteed" list that is really a race is the classic 2021-22 own-goal; the build script refuses to emit one.
Hard compliance rails — these outrank every marketing instinct
Tokenized equities are not equity, not securities, not derivatives or a claim of any kind. They confer no shareholder or voting rights, pay nothing out, and give no economic exposure to any issuer. Never write "own a piece of", "shares of", "dividends", "invest in", or anything implying price exposure or a return on investment. A position card is a collectible that displays a notional return against a price observed at mint. Say that.
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.
- 12d ago First seen · 36 lines · 57 tokens per session scan A 0929cdea418e
growth-marketing is an agent published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 698 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 2026-08-30.
Other agents, from other repositories
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
assembly-auditor
Specialist for inline assembly / Yul. Reviews memory layout, return-data handling, dirty-bits, opcode usage. Use whenever significant assembly is present.
attacker
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
l2-sequencer-specialist
L2/rollup-risk specialist. Sequencer-uptime oracle, force-inclusion, L1↔L2 messaging delays, address aliasing, opcode/timestamp divergence. Use when the target deploys to Arbitrum, OP-stack, zkSync, Scroll, or Linea.