wave-spec

A planning workflow for multi-day or multi-session projects. It creates shared specification, plan, worker-brief, status, and handoff files in the repository before work begins.

In plain words
What is it for?
Use it to plan development, content, translations, site rebuilds, or other one-to-three-week projects before execution.
Why use it?
It prevents a longer project from starting without an agreed plan and makes progress easier to resume across sessions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dimkurilo/opencode-skills/wave-spec
Any agent
npx skills add dimkurilo/opencode-skills --skill wave-spec
Clone the repo
git clone --depth 1 https://github.com/dimkurilo/opencode-skills

Made for: Claude Code, Codex.

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,378 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00155 $0.15378
Opus 5 $0.00077 $0.07689
Sonnet 5 $0.00031 $0.03076
Haiku 4.5 $0.00015 $0.01538

Measured 3d ago against content hash 9a0c94e256a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wave-spec scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/test_update_review_packet.py, scripts/update_review_packet.py, scripts/verify-handoff-payload.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `done_when` = **исполняемая команда** (grep/test/curl) или проверяемый факт; проза — только если команды нет.
skills/wave-spec/SKILL.md · 777 lines

How it starts

The opening of the file, as written. The whole thing — 777 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wave-spec

Method: same as vv-opencode (vv-specvv-plan → approve → exec), but portable: structured XML artifacts in the repo, any orchestrator CLI.

You (the agent) execute this skill. The user does not need to invent the pipeline.

Positioning (identity): wave-spec is a universal plan-gate + lifecycle skill for 1–3 week product waves across any domain — development, content, skill-port, translation, orchestration, site rebuild. It is NOT an SEO costume and NOT gsd-core / gsd-coordinator / vv-opencode runtime — no agentic dispatch, no worktree groups, no structured handoff beyond project-local SESSION_HANDOFF. The lifecycle gates below are the contract; full identity and boundaries in Positioning.

TL;DR (minimum path — 5 минут)

wave-spec = план-гейт. Пишет в waves/<date>-<slug>/: INTENT → SPEC.xml → PLAN.xml → approve → exec → STATUS/handoff. Не для однострочных правок (для них mode=quick).

Прочитай только: Modes → Hard gate → Pipeline шаги 0–5 → approve. Остальное (NEXT_SESSION/Linear) — по мере возникновения; LAUNCH.md обязателен для wave/program до dispatch (см. Шаг 6.0).

Лестница обучения: Волна 1 = mode=quick (весь цикл за 1 сессию) → Волна 2 = полный wave + 1 review → Волна 3+ = multi-model-orchestration. Учись деланием, не чтением.

Роутер: новый проект → project-bootstrap · план спринта → wave-spec · 2+ модели → multi-model-orchestration.

Modes

Mode Trigger Output
quick Trivial / пет-проект: ≤1 файл, ≤30 мин, no deploy INTENT 5 строк → SPEC 10 строк → approve → apply → archive (1 файл, без LAUNCH/NEXT_SESSION/Linear)
wave (default) One sprint 2–7 days / one theme waves/<date>-<slug>/…
task Single atomic task inside approved wave waves/.../tasks/TNN-*.xml + worker brief
program Multi-wave portfolio (fidelity port, book translation, site rebuild) — редко; см. references/program-maps.md roadmap/PROGRAM_SPEC.xml + roadmap/PROGRAM_PLAN.xml

Read the full file on GitHub · 777 lines

Changes

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.

  1. 3d ago First seen · 777 lines · 155 tokens per session scan A 9a0c94e256a8

Subscribe to this mod's changes

wave-spec is a skill published in the GitHub repository dimkurilo/opencode-skills (6 stars, last pushed 20d ago), licensed MIT. It adds 155 tokens to every session and 15,378 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens