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 skills/evolplus/talos/sa-architecture-designnpx skills add evolplus/talos --skill sa-architecture-designgit clone --depth 1 https://github.com/evolplus/talosWrote 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/evolplus/talos/sa-architecture-design)<a href="https://agentmods.dev/skills/evolplus/talos/sa-architecture-design"><img src="https://agentmods.dev/badge/skills/evolplus/talos/sa-architecture-design.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 5.1 | $0.00092 | $0.00919 |
| Opus 5 | $0.00046 | $0.00460 |
| Sonnet 5 | $0.00018 | $0.00184 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
sa-architecture-design 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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SA Architecture Design
Use
Use this skill when SA is dispatched in design mode. Do not use for brownfield extraction or external-integration adequacy; those have separate skills.
Inputs
docs/SRS.mdatStatus: Signed-offdocs/user-stories/,docs/frs/,docs/external-integrations/- Existing
docs/architecture.mdanddocs/decisions/when revising - SRS headers
Designated Dependency Approver,Frontend-Framework,Backend-Track,Backend-Framework solution-defaults,third-party-dependency-evaluation,adr-author,c4-author,data-lifecycle-contracts,format-boundary-contracts
Outputs
docs/architecture.mdusingagents/_templates/_artifacts/architecture-template.md.- ADRs under
docs/decisions/for every non-trivial choice. docs/instrumentation-contract.mdfor any SRS with a UI surface.docs/open-issues.mdentries for architectural gaps that cannot be resolved from the SRS.- Worktree
plan-update.jsonwithtrack: "sa".
Procedure
- Verify SRS is signed off. Halt if not.
- Read the SRS, every linked US/FR, external integration files, and prior ADRs.
- Build C4 levels:
- C1 Context: system boundary, actors, external systems.
- C2 Containers: runnable/deployable units, datastores, queues, clients.
- C3 Components: required for non-trivial containers; each component row carries
Linked FRs. - Do not author C4 Code; Dev roles own code-level artifacts.
- Fill architecture sections:
- §3.5 Data Models when persistent state exists.
- §3.6 API Inventory for REST/gRPC/GraphQL/WebSocket/events/queues, linking contract files.
- §3.7 Dependency & Call Graph for cross-container calls, internal packages, and production dependencies.
- §3.8 Async Workflows for event/queue flows.
- Cross-cutting concerns, failure modes, NFR posture, open risks, and observability.
- Apply data-contract skills:
- Use
format-boundary-contractsfor fields crossing incompatible formats. - Use
data-lifecycle-contractsfor gate fields read by one component and written by another.
- Use
- For UI-bearing SRSs, author
docs/instrumentation-contract.mddeclaring stable test IDs/accessibility identifiers for FE Dev and QA. - For every non-trivial architectural choice, author an ADR.
- For new third-party dependencies:
- Check
solution-defaultsfirst. - Reuse prior ADR approvals when valid.
- Otherwise evaluate 2-4 options with
third-party-dependency-evaluation, halt withNEEDS_CONTEXT, and wait for the Designated Dependency Approver. - Do not include the dependency in accepted architecture until approval is recorded.
- Check
- Run a self-containment check on produced artifacts.
- Commit changes, then emit
plan-update.json.
What ships with it
1 file 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.
- 6d ago First seen · 73 lines · 92 tokens per session scan A abb8f7ed5faa
sa-architecture-design is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 919 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…