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/tqnonline/agent-forge/backlog-decomposenpx skills add tqnonline/agent-forge --skill backlog-decomposegit clone --depth 1 https://github.com/tqnonline/agent-forgeWrote 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/tqnonline/agent-forge/backlog-decompose)<a href="https://agentmods.dev/skills/tqnonline/agent-forge/backlog-decompose"><img src="https://agentmods.dev/badge/skills/tqnonline/agent-forge/backlog-decompose.svg" alt="Measured on agentmods" 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 | $0.00180 | $0.01541 |
| Opus 5 | $0.00090 | $0.00771 |
| Sonnet 5 | $0.00036 | $0.00308 |
| Haiku 4.5 | $0.00018 | $0.00154 |
Grade A, and why
backlog-decompose 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 4d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Decomposition
Version: 1.0 | Role: Senior Technical Product Manager & Backlog Architect Methodology: Receive > Decompose > Hand Off
You are a senior Technical Product Manager. You take finalized PRDs -- from prd-draft or prd-review -- and decompose them into a platform-neutral hierarchical backlog. You produce structured Markdown files that downstream exporter skills (backlog-ado, backlog-linear, backlog-github) consume.
Prerequisites
- Finalized PRD must exist in
{project}/specs/prd/before this skill runs - If no PRD exists, invoke
/prd-draftfirst and return here after completion
Phase 1: Receive
Use AskUserQuestion to gather context:
- PRD location: Confirm file path within
{project}/specs/prd/ - Backlog scope: Full PRD decomposition or specific sections only
- Story point scale: Fibonacci (1,2,3,5,8,13) | T-shirt (S=2, M=5, L=8, XL=13) | Custom
Read the PRD completely. Extract: product vision, user personas, functional requirements, non-functional requirements, technical constraints, success metrics, risks, dependencies. Confirm understanding with the user before proceeding.
Phase 2: Decompose
Transform PRD content into 7 work item types using these rules:
| # | Type | Source | Rule |
|---|---|---|---|
| 1 | Epic | Major product capabilities or value streams | 1 epic per major capability |
| 2 | Feature | Functional groupings within an epic | 2-6 features per epic |
| 3 | User Story | Individual user-facing requirements | Format: "As a [persona], I want to [action] so that [benefit]" |
| 4 | Technical User Story | Infrastructure, DevOps, security, performance needs | Format: technical requirement with validation criteria |
| 5 | Risk | Identified risks from the PRD | Include likelihood and impact assessment |
| 6 | Impediment | Known blockers, external dependencies, licensing | Include root cause and potential solutions |
| 7 | CI Item | Tech debt, monitoring, observability, documentation | Include expected benefit |
What ships with it
8 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.
- .skillrc 754 B
- references/_index/backlog-framework-overview.md 6.8 KB
- references/_index/quick-reference.md 6.6 KB
- references/methodology/cross-reference-strategy.md 8.1 KB
- references/methodology/prd-to-backlog-decomposition.md 11 KB
- references/methodology/technical-story-generation.md 9.8 KB
- references/templates/backlog-markdown-template.md 8.7 KB
- references/templates/backlog-summary-template.md 7.6 KB
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.
- 4d ago First seen · 132 lines · 180 tokens per session scan A 39bd0dc223c2
backlog-decompose is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 180 tokens to every session and 1,541 once invoked, about $0.0009 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
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
glab-issue
Create, view, update, and manage GitLab issues. Use when working with issue tracking, bug reports, feature requests, or task management. Operations include creating issues, listing with filters, viewing details, adding comments/notes, updating labels/assignees/milestones, closing/reopening, and board management.…
sales-ops
Set up and run Airtable-based sales operations and CRM workflows — pipeline management, account and renewal management, deal desk, RFP / tender pipelines, partner CRMs, sales forecasting, vertical CRMs (real estate, mortgage, brokerage, capital markets, public works, nonprofit), and AI-native lean stacks…
jira
Search and manage Jira issues using JQL queries, create/update tickets, and manage workflows. Use when asked to find Jira tickets, check the backlog, manage sprints, track bugs, or work with Atlassian project management.
github
Use this skill when Enoch needs to coordinate work with GitHub: branches, pull requests, issues, reviews, comments, checks, and merges.