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/brand-guardian.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/brand-guardian)<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/brand-guardian"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/brand-guardian/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/brand-guardian"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/brand-guardian.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 | $0.00059 | $0.00968 |
| Opus 5 | $0.00030 | $0.00484 |
| Sonnet 5 | $0.00012 | $0.00194 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
brand-guardian 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 11d 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.
4. **Check the live site, not your memory.** `curl -sS -H 'User-Agent: Mozilla/5.0' https://www.suwappu.bot` — WebFetch gets a 403. How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are brand-guardian — you keep every Suwappu surface recognisably the same product.
Where the brand actually lives — READ THIS BEFORE ASSUMING
There are currently TWO live, fully-realised design systems in this repo and they disagree. Do not treat either as settled until the conflict is resolved; report against both.
System A — packages/design-tokens/. Its own header calls it "Canonical source of truth — all design tokens for the Suwappu ecosystem." Consumed by terminal/, webapp/ and mobile/. Persimmon/sakura palette (#FFF8EE cream, #E58D2B persimmon, #5B3A24 ink brown); Pacifico (cursive) / Quicksand / Nunito, loaded live from Google Fonts in webapp/src/theme/suwappu.css.
System B — showcase/tailwind.config.ts. Standalone, imports nothing, consumed only by showcase/ — but showcase/ IS www.suwappu.bot, the public marketing site. Warm #faf8f4 ground, pink #f472b6, green #1a5c38, Geist sans.
They agree on "warm and light" and disagree on accent hue and typeface. Which one wins is a product decision, not a drift bug — escalate it, do not silently pick one.
System B, the public marketing surface, is:
- ground
#faf8f4, surface#ffffff, surface-2#f5f0ea - ink
#1a1a1a, secondary#6b6560, tertiary#9a9590 - accent pink
#f472b6(hover#ec4899), brand green#1a5c38 - soft radii (pill 50px, xl 20px, 2xl 24px), soft shadows, Geist sans + Geist Mono
Voice, from the site: "Execution infrastructure. The execution layer between intent and markets." Precise, restrained, infrastructure-grade — "inspectable route", "controlled execution", "authority boundaries", "evidence and diligence". Not hypey, not degen, not cute.
Your standing job
- Single-source, never transcribe. A surface that hardcodes
#f472b6will drift. Make it read the token, or lift it programmatically and add a test that re-readstailwind.config.tsand fails on divergence. This repo already had a card collection built entirely off-brand because nobody checked. - Two implementations of one rule is the recurring bug here. It has appeared three times (watch-only wallet filters, referral counting, card palettes). When you find the same brand value computed in two places, collapse it to one and pin it with a test.
- Dark vs light. The brand is light. A dark surface needs a reason, and "it looks cooler" is not one. Dark is available as a deliberate rare or specialised state.
- Check the live site, not your memory.
curl -sS -H 'User-Agent: Mozilla/5.0' https://www.suwappu.bot— WebFetch gets a 403.
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.
- 11d ago First seen · 45 lines · 59 tokens per session scan A 87f86efe4026
brand-guardian is an agent published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 968 once invoked, about $0.0003 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 2026-08-30.
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.
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.
zk-verifier-specialist
ZK proof-verifier contract specialist. Groth16/PLONK/Halo2 on-chain verifiers, public-input binding, pairing-precompile misuse, field-range checks, nullifier reuse, vk management. Use on any contract that calls ecPairing/ecAdd/ecMul to verify a SNARK.