WBSGenerator

WBSGenerator is an agent for Claude Code from attilaszasz/sdd-pilot. It costs 21 tokens per session (1,931 once invoked), scanned A, original, MIT.

An agent that creates a dependency-aware tasks.md file from a feature’s design and planning documents.

In plain words
What is it for?
Use it to create task lists for product, technical, or operational features from files such as spec.md and plan.md.
Why use it?
It turns product requirements, technical details, and implementation plans into ordered work items while checking that the required format and coverage are valid.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to create task lists for product, technical, or operational features from files such as spec.md and plan.md.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/attilaszasz/sdd-pilot/_wbs-generator
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.

Clone the repo
git clone --depth 1 https://github.com/attilaszasz/sdd-pilot

Made for: Claude Code.

Wrote 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.

agentmods badge for WBSGenerator

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_wbs-generator/github.svg)](https://agentmods.dev/agents/attilaszasz/sdd-pilot/_wbs-generator)
Your own site
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_wbs-generator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_wbs-generator/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.

agentmods 80×15 button for WBSGenerator

Your own site · 80×15
<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_wbs-generator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_wbs-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,931 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00021 $0.01931
Opus 5 $0.00010 $0.00966
Sonnet 5 $0.00004 $0.00386
Haiku 4.5 $0.00002 $0.00193

Measured 9d ago against content hash fd31f7888e1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

WBSGenerator 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 9d 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.

.github/agents/_wbs-generator.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Generate dependency-aware tasks.md from planning artifacts.

Inputs

Feature directory and available design documents.

Execution Rules

Enforce strict task format, sequencing, and self-validation before write.

Output Format

Return a JSON summary with task counts and work-item coverage.

0. Acquire Skills

Read .github/skills/task-generation/SKILL.md for Task Format, Phase Structure, and dependency rules.

1. Analyze Design

From FEATURE_DIR/spec.md extract:

  • spec_type from frontmatter (default product)
  • Product specs: User Stories + priorities; Technical/Operational: Objectives + priorities
  • Scenario-style criteria; requirements (FR-###, TR-###, OR-###, RR-###)

From FEATURE_DIR/plan.md extract:

  • Tech stack, project structure/file paths, implementation phases
  • Repo/workspace delta from Testing Strategy (or legacy QC Tooling) and Source Code sections
  • Requirement Coverage Map (if present): Req ID → Component(s) → File Path(s) → Function(s)/Symbol(s). The Function(s)/Symbol(s) column is the authoritative source for → exports: annotations — prefer its named symbols over re-deriving from prose.

Determine project mode:

  • Greenfield: initial project/workspace setup is part of feature
  • Brownfield: extends existing codebase; avoid generic bootstrap tasks
  • Mixed: targeted repo/workspace changes plus enhancement work

Set HAS_ANNOTATION_SOURCES = true when at least one of these sources exists: data-model.md, contracts/, or a Requirement Coverage Map row in plan.md with a populated Function(s)/Symbol(s) column (symbol-level detail sufficient to name imports/exports). When false, omit all → exports: and ← T###: annotations — fall back to description-only tasks.

2. Draft Task List

Generate tasks.md per skill Phase Structure:

  • Optional preamble: Project Mode, Epic / Capability Map, Brownfield Notes
  • Phase 1: Setup — only when feature changes repo-root tooling/config/scaffolding
  • Phase 2: Foundational — only for true cross-work-item blockers
  • Phase 3+: Delivery — grouped by US# (product) or OBJ# (technical/operational)
  • Final Phase: Polish — only when cross-cutting work remains

Read the full file on GitHub · 108 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. 9d ago First seen · 108 lines · 21 tokens per session scan A fd31f7888e1c

Subscribe to this mod's changes

WBSGenerator is an agent published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 1,931 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 2026-08-30.