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/rakovi4/continue-framework/architecturenpx skills add rakovi4/continue-framework --skill architecturegit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00068 | $0.00554 |
| Opus 5 | $0.00034 | $0.00277 |
| Sonnet 5 | $0.00014 | $0.00111 |
| Haiku 4.5 | $0.00007 | $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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architecture - Architectural Decision Record
Usage
/architecture 2 "task ordering within columns" # Story 2, named decision
/architecture 10 # Story 10, discover topic interactively
/architecture # Detect from recent git log
Purpose
When implementation reveals a design fork — multiple viable approaches with different trade-offs — this skill pauses coding to think through the options, document the decision, and plan the implementation with proper TDD steps.
Workflow
Phase 1: Context Gathering
- Resolve story from argument (same resolution as
/continue) - Read the story spec, current progress, relevant test specs, and existing ADRs
- Read the code involved — domain entities, usecases, adapters, schemas
- Summarize the decision point: what question needs answering, what triggered it, what constraints exist
Phase 2: Interactive Discussion
- Present the problem — describe the tension or fork point clearly
- Propose 2-4 options with trade-offs (how it works, pros/cons, impact, edge cases)
- Request a user decision using structured input when available, otherwise ask directly; pause so the developer can choose or propose alternatives
- Iterate until the approach is clear
- Draw diagrams when helpful — write HTML files to visualize complex flows
Phase 3: Write ADR
Use the format from .claude/templates/spec/adr-format.md.
Phase 4: Update Test Specs
Add edge case scenarios discovered during discussion to the appropriate test spec file.
Phase 5: Update Progress
Update progress.md with TDD steps that implement the decision.
Phase 6: Commit
Commit message: Story N: ADR for {decision topic} (Scenario X)
Rules
- Never generate code during this skill — it's a planning tool
- Always read existing ADRs in the story's
decisions/subfolder to avoid contradicting prior decisions - The developer makes the final call — present options, don't prescribe
- Keep ADRs concise — include current schema/code state when relevant
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.
- 3d ago First seen · 63 lines · 68 tokens per session scan A 86ebf62ecf89
architecture is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 554 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…