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/anthropics/knowledge-work-plugins/architecturenpx skills add anthropics/knowledge-work-plugins --skill architecturegit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWhat 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 | $0.00052 | $0.00553 |
| Opus 5 | $0.00026 | $0.00277 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
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 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- architecture — 100% identical, 0 lines differ
- architecture — 100% identical, 0 lines differ
- architecture-th — 89% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architecture
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Create an Architecture Decision Record (ADR) or evaluate a system design.
Usage
/architecture $ARGUMENTS
Modes
Create an ADR: "Should we use Kafka or SQS for our event bus?" Evaluate a design: "Review this microservices proposal" System design: "Design the notification system for our app"
See the system-design skill for detailed frameworks on requirements gathering, scalability analysis, and trade-off evaluation.
Output — ADR Format
# ADR-[number]: [Title]
**Status:** Proposed | Accepted | Deprecated | Superseded
**Date:** [Date]
**Deciders:** [Who needs to sign off]
## Context
[What is the situation? What forces are at play?]
## Decision
[What is the change we're proposing?]
## Options Considered
### Option A: [Name]
| Dimension | Assessment |
|-----------|------------|
| Complexity | [Low/Med/High] |
| Cost | [Assessment] |
| Scalability | [Assessment] |
| Team familiarity | [Assessment] |
**Pros:** [List]
**Cons:** [List]
### Option B: [Name]
[Same format]
## Trade-off Analysis
[Key trade-offs between options with clear reasoning]
## Consequences
- [What becomes easier]
- [What becomes harder]
- [What we'll need to revisit]
## Action Items
1. [ ] [Implementation step]
2. [ ] [Follow-up]
If Connectors Available
If ~~knowledge base is connected:
- Search for prior ADRs and design docs
- Find relevant technical context
If ~~project tracker is connected:
- Link to related epics and tickets
- Create implementation tasks
Tips
- State constraints upfront — "We need to ship in 2 weeks" or "Must handle 10K rps" shapes the answer.
- Name your options — Even if you're leaning one way, I'll give a more balanced analysis with explicit alternatives.
- Include non-functional requirements — Latency, cost, team expertise, and maintenance burden matter as much as features.
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 · 86 lines · 52 tokens per session scan A de7db3170a3a
architecture is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 553 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.