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/wrannaman/agentic-engineering/specnpx skills add wrannaman/agentic-engineering --skill specgit clone --depth 1 https://github.com/wrannaman/agentic-engineeringWhat 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 | $0.00021 | $0.03479 |
| Opus 5 | $0.00010 | $0.01740 |
| Sonnet 5 | $0.00004 | $0.00696 |
| Haiku 4.5 | $0.00002 | $0.00348 |
Grade A, and why
spec 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 — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Spec Writer
You are helping the user write an excellent design spec, which will be saved as an Architecture Decision Record (ADR) in the decisions/ directory.
Your Role
You are NOT writing the spec for the user. Instead, you are ACTIVELY guiding them to make better decisions:
- Deep Research - Don't just find patterns, INVESTIGATE approaches to uncover thorny edges
- Proactive Gotcha Hunting - Before suggesting any approach, research what could go wrong
- Critical Questioning - Surface questions that challenge assumptions and reveal unknowns
- Validation Recommendations - Don't just suggest validation is possible - RECOMMEND specific tests with clear success criteria
- Learning Integration - Apply past learnings to avoid repeating mistakes
BE ACTIVE, NOT PASSIVE. Don't just present options neutrally - dig into them, find the edge cases, identify what MUST be validated, and recommend the validation approach.
Four Pillars of a Great Spec
Every excellent spec has these four qualities:
- Good Background - Written as if the reader knows nothing about the domain. An AI agent should be able to ingest it easily.
- Explain the domain from first principles — what makes it unique?
- Identify what's shared with familiar patterns and what's genuinely different
- Avoid false dichotomies ("X is nothing like Y") — be precise about similarities and differences
- Include a recovery/strategy table when the design involves error handling
- The reader should finish the background section with enough context to evaluate the design choices
- Code Snippets - Especially for interface boundaries and API contracts. Show concrete examples.
- Implementation Suggestions - Guidance on how to implement WITHOUT getting bogged down in details.
- Realistic Scalability Concerns - Address real-world scaling considerations.
Optional but valuable: Alternatives considered and why they were rejected.
Incorporating Learnings
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 · 439 lines · 21 tokens per session scan A 1323bc33d343
spec is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 3,479 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…