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/leifericf/agentic-sdk/describe-problemnpx skills add leifericf/agentic-sdk --skill describe-problemgit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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 | $0.00015 | $0.00409 |
| Opus 5 | $0.00008 | $0.00204 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
describe-problem 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.
What it actually says
describe-problem
Clarify the real user problem, constraints, and success criteria in user and business terms. Define WHAT, not HOW.
Procedure
- Read
~/.agentic-sdk/<project>/artifacts/project/project-meta.mdand~/.agentic-sdk/<project>/artifacts/decisions/open-questions.md. If either is missing, returnblocked: bootstrap the planning artifacts first. - Collect a single-paragraph problem statement from the dispatch prompt; accept rough notes or bullets.
- Clarify through follow-ups, at most three per turn: who experiences the problem, what observable success looks like, what is in and out of scope, the constraints (technical, operational, legal, integration, budget), and the risks and unknowns. Surface hidden complexity and assumptions; challenge vague words ("fast", "secure") into concrete definitions.
- Iterate until the problem is understood and the summary is confirmed.
Park unresolved questions in
open-questions.mdunderOpenas- [ ] [Affects: problem-description.md] <question> (Answer: TBD); mark[Blocking]only if you cannot proceed. - Write
~/.agentic-sdk/<project>/artifacts/planning/problem-description.mdwith these sections: Metadata, Summary, Problem, Desired Outcomes, Stakeholders, Current Workflows, In Scope, Out of Scope, Constraints, Risks, Unknowns, Simplification Opportunities, References.
Boundaries
Owns the problem in user and business terms. define-requirements owns the testable requirements; design-technical owns the architecture. Reached by plan-system.
Return
One line: the artifact written and a terse status, or blocked: <reason>.
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 · 42 lines · 15 tokens per session scan A e1df54c9d486
describe-problem is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 14d ago), licensed MIT. It adds 15 tokens to every session and 409 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…