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 gear-foundation/vara-skills --skill sails-architecturegit clone --depth 1 https://github.com/gear-foundation/vara-skillsWrote 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/gear-foundation/vara-skills/sails-architecture)<a href="https://agentmods.dev/skills/gear-foundation/vara-skills/sails-architecture"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-architecture/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/gear-foundation/vara-skills/sails-architecture"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-architecture.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 | $0.00054 | $0.01339 |
| Opus 5 | $0.00027 | $0.00669 |
| Sonnet 5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
sails-architecture 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 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.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sails Architecture
Goal
Turn an approved spec into a Sails-specific architecture artifact before implementation starts.
If the work changes a released contract or introduces a new deployed contract version, the architecture note must also define compatibility expectations for public routes, replies, events, generated clients, and off-chain consumers such as frontend and indexer.
Inputs
../../assets/architecture-template.md../../references/vara-domain-overview.md../../references/sails-cheatsheet.md../../references/gear-sails-production-patterns.md../../references/sails-program-and-service-architecture.md../../references/gear-messaging-and-replies.md../../references/gear-gas-reservations-and-waitlist.md../../references/awesome-sails-token-patterns.md../../references/contract-interface-evolution.md../../references/sails-header-wire-format.md— interface ID stability, entry ID derivation, route index
Write the result to docs/plans/YYYY-MM-DD-<topic>-architecture.md.
Execution Model Checks
- Model deferred work with delayed messages across future blocks, not off-chain cron as the default. A program can send a delayed message to itself or another actor when it must revisit state later.
- If the design depends on future execution budget, call out reserved gas or
ReservationIdusage and duration explicitly. Reservation keeps gas available for later sends, including delayed sends, but it is not free, permanent, or a value transfer. - Treat the Waitlist as on-chain storage for messages awaiting processing or conditions, not as a normal mempool.
- Waitlisted messages incur rent or locked-fund costs over time, can expire at a maximum duration, and cannot be prolonged indefinitely.
Route Deeper When Needed
- If the architecture question is whether Gear or Sails exposes the right API family, review
../gear-gstd-api-map/SKILL.mdfirst. - If the architecture risk is mostly around replies, timeouts, delayed work, or reservations, review
../gear-message-execution/SKILL.md. - If the architecture introduces a fungible token, token-backed accounting, or token-manager split, review
../../references/awesome-sails-token-patterns.md. - If a service wraps a runtime builtin actor (staking broker, proxy broker, BLS helper, ETH bridge sender), review
../gear-builtin-actors/SKILL.md— state ownership, idempotency, and reply routing differ from program-to-program calls because the builtin has no memory or code.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 95 lines · 54 tokens per session scan A d1c1989d0bdd
sails-architecture is a skill published in the GitHub repository gear-foundation/vara-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,339 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 skills, from other repositories
web3-fullstack-packaged-build
Systematic full-stack Web3 build with mandatory packaging and delivery phase.
web3-fullstack-systematic-build
Systematic approach to building full-stack Web3 applications layer by layer.
solana-dev
Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my Solana program", "deploy to devnet", "send a v1 transaction", "support larger transactions", "fix maxSupportedTransactionVersion", or "explain…
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…
walkeros-create-destination
Use when creating a new walkerOS destination to send events to a vendor or API (GA4/gtag, Meta/Facebook Pixel, Mixpanel, Amplitude, a custom HTTP API, Measurement Protocol), web or server-side. Example-driven workflow: research the vendor SDK and define step examples before implementing the destination interface, env…
walkeros-create-source
Use when creating a new walkerOS source to capture events (browser source, dataLayer interception, server/HTTP source, webhook receiver, event capture), web or server-side. Example-driven workflow: research the input format and define step examples before implementing the push interface, createTrigger, and env pattern.