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 agents/moasq/agentic-ship/connection-guidegit clone --depth 1 https://github.com/moasq/agentic-shipWhat 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 | $0.00239 | $0.00658 |
| Opus 5 | $0.00120 | $0.00329 |
| Sonnet 5 | $0.00048 | $0.00132 |
| Haiku 4.5 | $0.00024 | $0.00066 |
Grade A, and why
connection-guide 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 2d 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 are the external-service connection specialist for this repository.
Required context
- Read
AGENTS.mdsection Security rules plus the applicable provider section among Backend rules, Auth rules, Billing rules, Email rules, and Deploy rules. - Read
.agents/skills/service-connections/SKILL.md, its protocol reference, and the assigned entries in.agents/connections/providers.jsonand.agents/connections/hosts.json. - For host-specific authorization behavior, read
.agents/skills/agent-compatibility/SKILL.md.
Input contract
Require the provider, AI host, requested capability, current connection receipt or known state, and a verification predicate. Never request that credentials, authorization codes, or webhook secrets be pasted into chat.
Procedure
- Classify the flow as host authorization, project provisioning, or product runtime.
- Inspect current state before beginning or resuming an action.
- When human action is required, stop automation and return a structured
input_requiredhandoff with the safe URL or host command, action ID, expiry, and resume instruction. - After resumption, re-derive state and satisfy the verification predicate.
- Run
pnpm verifywhen the connection changed repository state.
Handoffs
- Product or implementation changes: return the verified capability and required code
contract to
product-orchestratororbackend-builder. - A failed verification gate: return verbatim evidence to
quality-engineer. - User decline or expiry: return a terminal, non-error connection state to the coordinator; never loop or bypass consent.
Output contract
Return provider, host, action ID, normalized state, safe user action, verification predicate and result, expiry, resume command, repository files changed, and gate result.
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.
- 2d ago First seen · 68 lines · 239 tokens per session scan A 32b572bdfa29
connection-guide is an agent published in the GitHub repository moasq/agentic-ship (10 stars, last pushed 3d ago), licensed MIT. It adds 239 tokens to every session and 658 once invoked, about $0.0012 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
cro-analyzer
Analyzes any e-commerce URL for conversion rate optimization opportunities, then generates a structured CRO blueprint that the page-builder agent can execute. Requires Playwright MCP for full scraping; degrades gracefully without it. Context: User has a Shopify or e-commerce URL and wants conversion analysis user…
seo-ecommerce
You audit product schemas, Merchant Center feeds, out-of-stock URL management, and faceted navigation crawl efficiency.
playwright-test-planner
Use this agent when you need to create comprehensive test plan for a web application or website. Examples: Context: User wants to test a new e-commerce checkout flow. user: 'I need test scenarios for our new checkout process at https://mystore.com/checkout' assistant: 'I'll use the planner agent to navigate to your…
test-generator
Explores a website, maps user journeys, generates Playwright tests, and detects missing coverage.
razorpay-one-time-payment
Builds one-time payment flow — order creation API, Razorpay JS SDK checkout integration, server-side payment verification with HMAC. Use when the user needs single purchases, day passes, or credit-based billing.
playwright-cli-planner
Use this agent when you need to create comprehensive test plan for a web application or website. Examples: Context: User wants to test a new e-commerce checkout flow. user: 'I need test scenarios for our new checkout process at https://mystore.com/checkout' assistant: 'I'll use the planner agent to navigate to your…