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 AstravueOrg/astravue-mcp-server --skill breaking-down-workgit clone --depth 1 https://github.com/AstravueOrg/astravue-mcp-serverWrote 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/astravueorg/astravue-mcp-server/breaking-down-work)<a href="https://agentmods.dev/skills/astravueorg/astravue-mcp-server/breaking-down-work"><img src="https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/breaking-down-work/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/astravueorg/astravue-mcp-server/breaking-down-work"><img src="https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/breaking-down-work.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 | $0.00081 | $0.00593 |
| Opus 5 | $0.00041 | $0.00296 |
| Sonnet 5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
breaking-down-work 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking Down Work
Turns a high-level goal into a complete, well-scoped task tree. The value is in the decomposition and sequencing — not in the tool calls — so spend effort on coverage and structure, then create in one confirmed pass.
Workflow
-
Understand the goal and scope
Clarify the deliverable and the target project. Use
astravue_list_projectsif the project is unclear. If the work hangs off an existing task, note its ID — the new tasks become subtasks of it. -
Decompose to full coverage
Break the goal into tasks, then subtasks, then checklist items where useful. Aim for the 100% rule: the children together fully cover the parent's scope with no overlap. A leaf is small enough when one person can finish it in a sitting and you can tell when it's done.
- Tasks — the main units of deliverable work
- Subtasks (
astravue_create_subtask) — steps within a task - Checklist items (
astravue_create_checklist_item) — acceptance criteria or fine-grained todos
-
Sequence the work
Identify which tasks block others. Capture these as dependencies. Flag anything that can run in parallel so the plan doesn't serialize work that needn't be.
-
Present the plan and confirm
Show the full tree (task → subtasks → checklist), proposed dependencies, and any estimates, as a structured outline. Ask the user to adjust or approve. Do not create anything before approval — decomposition is cheap to revise on paper and expensive to undo in the workspace.
-
Create after approval
astravue_bulk_create_tasks— create the top-level tasks in one callastravue_create_subtask— add subtasks under each taskastravue_create_checklist_item— add checklist itemsastravue_add_dependency— wire up the blocking relationships
Report back what was created with IDs so the user can navigate to it.
Important
- Decompose first, create once. The thinking is the deliverable; the writes are mechanical.
- Apply the 100% rule — if the children don't cover the parent, the breakdown is incomplete; if they overlap, it's redundant.
- Never create tasks before the user approves the plan.
- Only set estimates, assignees, or due dates the user actually provides — don't invent them.
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.
- 9d ago First seen · 47 lines · 81 tokens per session scan A 54b37c7866cf
breaking-down-work is a skill published in the GitHub repository AstravueOrg/astravue-mcp-server (12 stars, last pushed 15d ago), licensed Apache-2.0. It adds 81 tokens to every session and 593 once invoked, about $0.0004 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.
Other skills, from other repositories
pm-init
Skill "pm-init" from wei63w/pm-manager, covering user input, outline, 1. scaffold, 2. lifecycle and type and 3. detect spec kit (required).
pm-arch
Skill "pm-arch" from wei63w/pm-manager, covering user input, outline, done when and shared workflow (all /pm- commands).
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
pm-done
Skill "pm-done" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
pm-export
Export desensitized governance summary markdown for sharing or machine switch.
pm-outline
Generate detailed project outline and draft charter from user intent (empty/new projects).