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/douglance/sdlc-plugin/designnpx skills add douglance/sdlc-plugin --skill designgit clone --depth 1 https://github.com/douglance/sdlc-pluginWhat 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 | $0.00026 | $0.00552 |
| Opus 5 | $0.00013 | $0.00276 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use lifecycle-documentation only when the result needs a durable artifact or handoff.
Make the work precise. Design the interfaces and contracts, name the exact files and signatures, and define the architecture and its trade-offs. Specify how each unit of work will be verified.
Favor stable interfaces and the simplest design that meets the requirements. Don't over-build — every element of the design must trace to a requirement.
Ground every claim about the current architecture in exact path:line evidence and identify the closest existing implementation as prior art for each substantial boundary. When the design mainly preserves accumulated exceptions, run find-simplifying-insight and require a falsification test before replacing the current model.
What a design contains
- Interfaces and contracts — the boundaries between parts and what crosses them.
- Exact files and signatures — name them; leave no ambiguity for whoever builds.
- Trade-offs — the alternatives you considered and why you chose this one.
- Verification — a test or typecheck command for each unit of work.
Principles
Design for high cohesion (each module does one thing) and low coupling (modules depend on each other's interfaces, never their internals). Apply information hiding — put each likely-to-change decision behind an interface — so change stays local. Stable interfaces over clever internals; the simplest design that satisfies the requirements wins.
Architectural design
For system-wide structure — not just one module — make the architecture explicit:
- Stakeholders & concerns — who the design must satisfy (users, operators, security) and what each needs.
- Views — describe the system from the angles that matter: logical (modules and responsibilities), runtime (processes and data flow), deployment (where it runs). A diagram or a few lines each.
- Architecturally-significant decisions — the choices hard to reverse or that drive a quality attribute (performance, security, scalability). Record each as an ADR (see
documentation-and-adrs). - Tradeoff analysis — for each significant decision, list the options and score them against the quality attributes that matter, then pick with rationale rather than by default.
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 · 46 lines · 26 tokens per session scan A 974dae450a4e
design is a skill published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 552 once invoked, about $0.0001 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.
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…