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.
npx agentmods add commands/0xsoftboi/suwappubot/deploygit 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/commands/0xsoftboi/suwappubot/deploy)<a href="https://agentmods.dev/commands/0xsoftboi/suwappubot/deploy"><img src="https://agentmods.dev/badge/commands/0xsoftboi/suwappubot/deploy.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01415 |
| Opus 5 | $0.00017 | $0.00707 |
| Sonnet 5 | $0.00007 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
deploy 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 5d 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.
curl -s -o /dev/null -w "health=%{http_code}\n" https://api.suwappu.bot/health # expect 200 How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suwappu Deployment Skill (Railway)
Suwappu runs entirely on Railway — there is NO AWS/ECS/EC2 anymore. The old
AWS-ECS Telegram Mini App was abandoned on 2026-06-08 (commit e262711); app.suwappu.bot
now mirrors the terminal service. Ignore any older AWS/SSM/ECS instructions.
How deploys actually happen: auto on push to main
Railway is wired to GitHub via the deploy-railway.yml Action + per-service
watchPatterns. Merging to main auto-deploys any service whose watched paths changed.
You usually do NOT need to run anything — merge the PR and Railway rebuilds.
| Service | railway.*.json |
Dockerfile | watchPatterns (auto-deploy trigger) |
|---|---|---|---|
python-api (bot + FastAPI) |
railway.python-api.json |
api/Dockerfile.railway |
api/**, bot/**, database/**, requirements.txt |
python-worker (background tasks) |
railway.python-worker.json |
api/Dockerfile.railway |
api/**, bot/**, database/**, requirements.txt |
terminal (live Telegram Mini App — app.suwappu.bot + terminal.suwappu.bot) |
railway.terminal.json |
terminal/Dockerfile |
terminal/**, packages/design-tokens/** |
api-ts |
api-ts/railway.json |
api-ts/Dockerfile |
(root) |
showcase (www.suwappu.bot) |
showcase/railway.json |
showcase/Dockerfile |
(root) |
Other services in the project: suwappu-bridge, suwappu-relayer, Postgres, Redis.
webapp/ is DEAD — no Railway config, deployed nowhere. The live Mini App is terminal/.
Project: suwappu (id 428680a3-dd24-4f7c-8349-e66d791b5104), workspace "Eric Manganaro's Projects",
env production. python-api service id fed701e4-8fd9-47ec-9e1d-56bcceea1d90.
Manual deploy (emergency override / when you can't merge)
This machine has the railway CLI (no aws, no docker needed for source-upload deploys).
Deploy from a clean origin/main worktree so you never upload other sessions' uncommitted changes:
cd /home/mongolraider/suwappu
git fetch origin main
WT=/home/mongolraider/suwappu-wt-deploy
git worktree remove "$WT" --force 2>/dev/null || true
git worktree add --detach "$WT" origin/main
cd "$WT"
# Link this fresh worktree to the project/service (non-interactive):
railway link -p 428680a3-dd24-4f7c-8349-e66d791b5104 -e production -s <SERVICE>
railway up --service <SERVICE> --detach # uploads source, builds server-side
<SERVICE> = python-api | python-worker | terminal | api-ts | showcase.
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.
- 5d ago First seen · 84 lines · 35 tokens per session scan A ee8e2eef2791
deploy is a command published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,415 once invoked, about $0.0002 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 commands, from other repositories
debug-order
Debug why a CoW Protocol order failed to match.
krait
Run a complete multi-phase security audit on the target codebase.
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
krait-init
Standalone readiness check before running /krait. Verifies tools, project shape, gitignore, MCP wiring, and /.claude install. Reports what's missing — does NOT install or modify anything.
dashboard
Open the ChainGPT marketplace dashboard (localhost web UI — Overview, Skills, Activity, Health, About).