Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jpoutrin/product-forgenpx agentmods add skills/jpoutrin/product-forge/generate-tasksWrote 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/jpoutrin/product-forge/generate-tasks)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/generate-tasks"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/generate-tasks/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/jpoutrin/product-forge/generate-tasks"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/generate-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00014 | $0.00644 |
| Opus 5.5 | $0.00006 | $0.00258 |
| Sonnet 5.5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
generate-tasks 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-tasks
Category: Task Management
Usage
generate-tasks <prd-file> [--output-dir <directory>]
Arguments
<prd-file>: Required - Path to the PRD file to convert--output-dir: Optional - Directory for task file (default: ./tasks/)
Execution Instructions for Claude Code
When this command is run, Claude Code should:
- Read the PRD file and extract metadata
- Analyze PRD content to generate a comprehensive task list
- Create task file with proper naming convention:
- For
*-prd.md: create*-prd-tasks.md - For
*-frd.md: create*-frd-tasks.md - For
*-simple-frd.md: create*-simple-frd-tasks.md
- For
- Save task file in the specified output directory (create if needed)
- Update the PRD with a reference to the generated task file:
- Add or update the "Implementation Tracking" section
- Include task file path and generation date
- Follow any additional process in the source documentation
Task File Format
Generated task file should include:
# [PRD Title] Implementation Tasks
Source PRD: [relative path to PRD]
Generated: [date]
Total Tasks: [count]
Completed: 0
## Tasks
- [ ] 1.0 Setup and Configuration
- [ ] 1.1 Review relevant documentation
- [ ] 1.2 Set up development environment
- [ ] 2.0 Core Implementation
- [ ] 2.1 [Specific task based on PRD]
...
PRD Update
Add to PRD under "Implementation Tracking" section:
## Implementation Tracking
Task List: ./tasks/[filename]-tasks.md
Generated: 2025-01-06
Status: See task file for current progress
Source Content Location
The full process documentation can be found at:
claude_settings/python/shared/processes/task-generation.md
Claude Code should read this file and follow the documented process exactly.
Example
# Generate tasks in default location
generate-tasks user-auth-frd.md
# Generate tasks in specific directory
generate-tasks inventory-prd.md --output-dir ../tasks/
# Generate from PRD in another directory
generate-tasks ./drafts/feature-prd.md
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.
- 1mo ago First seen · 98 lines · 14 tokens per session scan A 97ad3f81e5ed
generate-tasks is a skill published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 644 once invoked, about $0.0001 per session on Opus 5.5. 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
remove
Remove a deployed framework or addon from the current workspace.