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 skills add nWave-ai/nWave --skill nw-jtbd-workflow-selectiongit clone --depth 1 https://github.com/nWave-ai/nWaveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nwave-ai/nwave/nw-jtbd-workflow-selection)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-jtbd-workflow-selection"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-jtbd-workflow-selection/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-jtbd-workflow-selection"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-jtbd-workflow-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.01441 |
| Opus 5 | $0.00019 | $0.00720 |
| Sonnet 5 | $0.00008 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
nw-jtbd-workflow-selection 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 6d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JTBD Workflow Selection
Classify incoming work by job type and recommend the appropriate nWave workflow entry point. Use during Phase 1 (GATHER) to triage before crafting stories.
ODI Two-Phase Framework
Determine which phase applies before proceeding.
Phase 1: Discovery -- when you do not know what to build
[research] --> discuss --> design --> distill
| | | |
GATHER WHAT are HOW should WHAT does
evidence the needs? it work? "done" look like?
Phase 2: Execution Loop -- when you know what needs to change
[research] --> baseline --> roadmap --> split --> execute --> review
| | | | | |
GATHER MEASURE PLAN it BREAK it DO each CHECK
evidence first completely into atoms task quality
|
<-----------+ (loop per task)
Key insight: research is a cross-wave capability invocable at any point for evidence-based decisions.
When to Skip Discovery
Skip discovery and enter execution loop directly when ALL hold:
- User already understands the problem domain
- Problem is identified and scoped
- No stakeholder alignment needed
- User can articulate what "done" looks like
If any fail, start with discovery (DISCUSS wave).
Five Job Types
Job 1: Build Something New (Greenfield)
"I need to create something that doesn't exist yet"
[research] -> discuss -> design -> [diagram] -> distill -> baseline -> roadmap -> split -> execute -> review
| Step | Purpose |
|---|---|
| research | (Optional) Gather domain knowledge before requirements |
| discuss | Gather requirements -- you don't know what's needed yet |
| design | Architecture decisions, technology selection |
| diagram | (Optional) Visualize architecture for stakeholders |
| distill | Define acceptance tests -- what does "done" look like? |
| baseline | Measure starting point for tracking improvement |
| roadmap | Comprehensive plan while context is fresh |
| split | Break into atomic, self-contained tasks |
| execute | Do each task with clean context |
| review | Quality gate before proceeding |
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.
- 6d ago First seen · 181 lines · 39 tokens per session scan A 8d3bc56f9887
nw-jtbd-workflow-selection is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 1,441 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 2026-09-03.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
planning
Create structured plan documents and track work items using YAML frontmatter. Use when the user wants to plan a feature, track progress, log bugs/tasks/ideas, or organize project work.
organize-task-files
Lists, pairs, deduplicates, and moves task files across the Coworker task state machine (0draft → 6git-pushed). Use when asked to organize, clean up, or audit task files.