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 aneja5/forge-skills --skill planning-and-task-breakdowngit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/planning-and-task-breakdown)<a href="https://agentmods.dev/skills/aneja5/forge-skills/planning-and-task-breakdown"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/planning-and-task-breakdown/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/aneja5/forge-skills/planning-and-task-breakdown"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/planning-and-task-breakdown.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 | $0.00058 | $0.02196 |
| Opus 5 | $0.00029 | $0.01098 |
| Sonnet 5 | $0.00012 | $0.00439 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
planning-and-task-breakdown 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning and Task Breakdown
Overview
Read .forge/prd.md, .forge/architecture.md, and .forge/contracts/ to produce .forge/tasks.yaml — a sized, dependency-ordered list of tasks where each task is a thin vertical slice through all layers. Output feeds incremental-implementation.
When to Use
.forge/prd.mdand.forge/architecture.mdboth exist- Ready to break work into implementable tasks before coding starts
- Need to identify dependencies and parallelize work
When NOT to Use
- Architecture doesn't exist yet — run
architecture-and-contractsfirst - PRD is not complete — gaps produce tasks with unknown scope
- Single-module change with no integration — implement directly with
tdd
Common Rationalizations
| Thought | Reality |
|---|---|
| "I can keep the task list in my head" | Tasks in your head have no acceptance criteria |
| "We'll figure out dependencies as we go" | Undiscovered dependencies stall work mid-implementation |
| "All tasks are the same size" | They never are — sizing forces honest scope assessment |
| "Vertical slicing is overkill here" | Horizontal slicing (all API, then all UI) delays feedback until integration |
| "Tasks can reference file paths" | File paths rot — describe behaviors and module names |
Red Flags
- Tasks that touch more than 3 modules (not a vertical slice — split it)
- No acceptance criteria per task (untestable)
- No dependency graph (implementation order unknown)
- Task descriptions name files/functions instead of behaviors
- XL tasks with no breakdown path (too much unknown — spike first)
- All tasks marked "no dependencies" (integration is being deferred)
Core Process
Step 1: Read the artifacts
Read .forge/prd.md for requirements. Read .forge/architecture.md for components. Read all files in .forge/contracts/ for module interfaces.
Step 2: Identify vertical slices
Each task must be a tracer bullet: a thin but complete path through ALL layers. Not "implement the API" — that's horizontal. Instead: "user can submit a form and see a success message" — that's a vertical slice cutting through UI, API, and storage.
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 · 177 lines · 58 tokens per session scan A 724a80ab3d1e
planning-and-task-breakdown is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 2,196 once invoked, about $0.0003 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
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
to-tickets
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.
lead
Use when acting as the factory tech lead: classify work, ask the minimum questions, create tickets, and dispatch without implementing.
swarm-swarm
Self-claiming pool orchestration. Workers race to claim tasks from a shared pool, loop until the pool is empty.
build-flow
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it.
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.