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/xiaolai/vmark/planningnpx skills add xiaolai/vmark --skill planninggit clone --depth 1 https://github.com/xiaolai/vmarkWhat 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 | $0.00038 | $0.01193 |
| Opus 5 | $0.00019 | $0.00596 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
planning 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Skill
When to use
Use this skill when the user asks for planning, a roadmap, a spec-to-implementation breakdown, or wants decisions documented.
Modes
Choose the lightest mode that meets the request.
quick-plan
Use when:
- task is small/medium and non-breaking
- no migrations and no multi-phase rollout
Output:
- 3–8 Work Items (WI-###), each with tests + acceptance
full-plan (default)
Use when:
- migrations/persistence changes
- API/contract changes (public tools, schemas, SDKs)
- multi-phase roadmaps
- performance-sensitive work
Output:
- structured plan sections (see “Plan file template”)
Process
-
Clarify outcomes
- Restate desired behaviors and constraints.
- Identify ambiguities and propose defaults if the user doesn’t decide.
- Capture constraints & dependencies (runtime versions, OS, external services, feature flags, required tools).
- Capture gaps: list requirement/behavior gaps or missing decisions revealed here.
-
Inventory current behavior
- Trace entry points → state/store → side effects → persistence.
- List key files/modules and the invariants they rely on.
- Note ownership/priority rules (windows, workspaces, files).
- Capture gaps: list where current behavior diverges from the stated outcomes.
-
Define target rules
- Convert outcomes into explicit rules and precedence.
- For each rule, include: trigger/context, expected behavior, scope, constraints, and exclusions.
- Edge-case pass: cover empty/none, invalid/malformed, boundary sizes, conflicting state, multi-surface coordination, persistence/restore, and I/O failures.
- Capture gaps: list rules that lack implementation support or current behavior conflicts.
- Create a Decision Log:
- decision, options considered, rationale, and why alternatives were rejected.
- Create an Open Questions list:
- questions that block correctness, who decides, and what the default is if not decided.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 131 lines · 38 tokens per session scan A eaa5bbe9faa4
planning is a skill published in the GitHub repository xiaolai/vmark (544 stars, last pushed 3d ago), licensed ISC. It adds 38 tokens to every session and 1,193 once invoked, about $0.0002 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…