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/sequenzia/claude-plugins/task-generationnpx skills add sequenzia/claude-plugins --skill task-generationgit clone --depth 1 https://github.com/sequenzia/claude-pluginsWhat 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 | $0.00033 | $0.01225 |
| Opus 5 | $0.00016 | $0.00613 |
| Sonnet 5 | $0.00007 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
task-generation 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Generation Skill
This skill provides structured knowledge for transforming Product Requirements Documents into Claude Code native Tasks with proper dependencies, metadata, and acceptance criteria.
Core Principles
1. Atomic Task Decomposition
Tasks should be:
- Single Responsibility: Each task accomplishes one specific outcome
- Independent: Minimal coupling with other tasks where possible
- Verifiable: Clear completion criteria that can be objectively assessed
- Estimable: Complexity can be reasonably assessed (XS/S/M/L/XL)
2. Layered Architecture Pattern
Decompose features following natural implementation layers:
Data Model → API/Service → Business Logic → UI/Frontend → Tests
This pattern ensures:
- Dependencies flow in one direction
- Each layer can be implemented and tested independently
- Integration points are well-defined
3. PRD-to-Task Traceability
Every task should trace back to the source PRD:
- Reference specific section numbers
- Quote relevant user stories
- Link acceptance criteria to PRD requirements
Task Schema
Each task created via TaskCreate follows this structure:
TaskCreate:
subject: "Create User data model" # Imperative mood
description: |
Define the User data model based on PRD section 7.3.
Fields:
- id: UUID (primary key)
- email: string (unique, required)
- passwordHash: string (required)
- createdAt: timestamp
Acceptance Criteria:
- [ ] Schema defined with all required fields
- [ ] Indexes created for email lookup
- [ ] Migration script created
Source: specs/PRD-Auth.md Section 7.3
activeForm: "Creating User data model" # Present continuous
metadata:
priority: critical # From PRD P0-P3
complexity: S # XS/S/M/L/XL
source_section: "7.3 Data Models" # PRD section reference
prd_path: "specs/PRD-Auth.md" # Source PRD
feature_name: "User Authentication" # Parent feature
task_uid: "specs/PRD-Auth.md:user-auth:model:001" # Unique ID for merge
What ships with it
2 files 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.
- yesterday First seen · 151 lines · 33 tokens per session scan A d47ced4fe228
task-generation is a skill published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 1,225 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…