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/genkovich/sdd/sequencesnpx skills add genkovich/sdd --skill sequencesgit clone --depth 1 https://github.com/genkovich/sddWhat 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 | $0.00172 | $0.03752 |
| Opus 5 | $0.00086 | $0.01876 |
| Sonnet 5 | $0.00034 | $0.00750 |
| Haiku 4.5 | $0.00017 | $0.00375 |
Grade A, and why
sequences 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: sequences
Draws the runtime view of an already-designed feature: for each critical flow it produces a Mermaid sequenceDiagram block — generic participants, happy path plus the error branches the spec demands — and writes them into docs/features/<slug>/sad.md §6. One flow at a time, user confirms each. The diagrams are the bridge between the static design (§5 building blocks) and the data layer: every persist/read step you draw becomes a hint for the indexes data-model will need.
Diagram labels + §6 prose follow artifact_language — but the existing sad.md's language wins over the setting; Mermaid keywords (sequenceDiagram, participant, alt/else/end) and participant names that name real modules stay English → ../_shared/artifact-language.md.
This skill keeps only its own machinery. Question phrasing is shared → ../_shared/ask-style.md. Flow count is driven by the spec, not a cap — every §4 user story / §5 acceptance criterion is covered (size may collapse detail, never coverage) → ../_shared/size-matrix.md. Each diagram is confirmed in prose, never as raw Mermaid → ../_shared/diagram-presentation.md; whether each flow is confirmed per-diagram or written-and-summarized follows the interview-depth setting → ../_shared/interview-depth.md.
Owner
Tech Lead (drives the runtime decomposition). The PM confirms that each drawn flow matches a real user story; a backend engineer flags persist steps that imply a new index.
Inputs
<slug>— same feature slug used by every earlier stage.- Gate (hard-refuse if missing):
docs/features/<slug>/sad.md. The §5 building-block view names the participants; §6 is where flows are written. Ifsad.mdis absent → STOP and point: «rundesign <slug>first — sequences are written into its §6». - (Expected)
sad.mdfrontmattertarget_surfaces— picks the participant vocabulary (UI-driven flows for a UI surface). Absent or empty → warn («surfaces undeclared — re-rundesign, or proceeding asbackend-service») and treat as[backend-service](→../_shared/surfaces.md); never silently guess a UI surface. - (Optional)
docs/features/<slug>/ux-flows.md— when it exists, the UI-driven flows drawn here agree with it: the<ui>steps follow the same screen path, and a flow may reference theSCR-NNid in a note; a divergence between a §6 flow and a ux-flow is surfaced, never silently drawn over. - Strongly expected:
docs/features/<slug>/spec.md— §4 user stories tell you which flows exist; §5 acceptance criteria are the coverage floor — every AC must be shown by a flow, a branch, or an explicit non-runtime N/A (the step-7 coverage check). Present by this stage in the normal pipeline; if genuinely absent, fall back to §6/§5 ofsad.mdfor the flow list and note that AC-coverage can't be verified. - (Optional)
docs/features/<slug>/.size— depth hint for detail (XS/S may collapse a flow's internal steps), never for coverage. Absent → default to M and say so loudly in the handoff — «size M (default — no.size; run/sdd:classify-size <slug>)». - (Optional)
.claude/sdd.local.mdinterview_depth(else medium) — governs only the diagram-confirmation UX (per-diagram prose+ask vs. write+summarize-and-proceed);sequencesdoes not open its own depth question (it honors the setting, or a--depth=arg if passed).
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.
- 3d ago First seen · 87 lines · 172 tokens per session scan A 858a094db58a
sequences is a skill published in the GitHub repository genkovich/sdd (118 stars, last pushed 14d ago), licensed MIT. It adds 172 tokens to every session and 3,752 once invoked, about $0.0009 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…