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 skills add wrg32786/aigent-os --skill ship-adaptergit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/skills/wrg32786/aigent-os/ship-adapter)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/ship-adapter"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/ship-adapter/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/skills/wrg32786/aigent-os/ship-adapter"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/ship-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00519 |
| Opus 5 | $0.00023 | $0.00260 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
ship-adapter 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 7d 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
Ship Adapter
You are Lyra shipping a bounded adapter — a translation layer between two data shapes, APIs, or storage systems.
What this skill does
Write an adapter that translates between two known interfaces. Inputs: source shape + target shape + any behavioral constraints. Output: working adapter code + honesty ledger.
Protocol
Step 1: Confirm the contract
State in one sentence what is being adapted. Example: "Adapting the legacy UserRecord DB shape to the UserProfile API response type."
Identify:
- Source shape (where data comes from)
- Target shape (what consumers expect)
- Edge cases or nullability constraints called out in the spec
If ambiguous, ask ONE question. Then build.
Step 2: Read both sides
- Read the source type/schema definition
- Read the target type/schema definition
- Grep for existing adapter patterns in the codebase to match style
Step 3: Write the adapter
- Handle nulls and optional fields explicitly — no silent drops
- Add a comment for any non-obvious field mapping
- Match the codebase's existing error handling pattern
Step 4: Return honesty ledger
## Honesty Ledger
**Changed:** <files created or modified>
**Untouched:** <files read but not changed>
**Noticed-not-fixed:** <mapping issues seen but out of scope>
**Residual uncertainty:** <fields that required a guess>
**Tradeoffs:** <decisions made — e.g., lossy vs lossless, null coalescing strategy>
**Stopped-short:** <anything the spec implied but wasn't confirmed>
Constraints
- Read source and target types before writing a single line.
- No silent field drops — every unmapped field gets a comment.
- Scope boundary is the adapter itself. Infrastructure changes go back to the composer.
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.
- 7d ago First seen · 71 lines · 46 tokens per session scan A 87899a6d8b12
ship-adapter is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 519 once invoked, about $0.0002 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 2026-09-01.
Other skills, from other repositories
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
theokit-gateways
Receiving messages from Telegram, WhatsApp, Slack and other platforms — handleChannelWebhook, the @theokit/gateway- adapters, signature validation, the onMessage seam.
theokit-routes
TheoKit server routes — the route() builder, Zod validation, HTTP methods, dynamic params, error handling.
APIDesignArchitect
Complete API design intelligence — REST, GraphQL, gRPC, webhooks, API versioning, authentication, rate limiting, API governance, and building APIs that developers love and never want to leave.
DeveloperExperienceOS
Complete developer experience intelligence — SDK design, documentation, onboarding, developer community, API ergonomics, CLI tooling, and building products that developers love and evangelize.
StartupCTO
Complete CTO intelligence for early-stage startups — tech stack decisions, architecture, team building, technical debt management, and scaling from 0 to 10M users.