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 PacificStudio/openase --skill task-breakdowngit clone --depth 1 https://github.com/PacificStudio/openaseWrote 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/pacificstudio/openase/task-breakdown)<a href="https://agentmods.dev/skills/pacificstudio/openase/task-breakdown"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/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/pacificstudio/openase/task-breakdown"><img src="https://agentmods.dev/badge/skills/pacificstudio/openase/task-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.01483 |
| Opus 5.5 | $0.00009 | $0.00593 |
| Sonnet 5.5 | $0.00005 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
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 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Breakdown
Overview
Use this skill after a requirement brief or spec already exists. Its job is to convert that clarified scope into a set of OpenASE tickets, parent-child relationships, and dependency edges that maximize safe parallelism without sacrificing phase-level deliverability.
This is not a generic "make a todo list" skill. It is a delivery design skill. It should produce tickets that are independently meaningful, testable, and strict enough that agents cannot declare victory after only shallow local edits.
When To Use
- A spec from
deep-interview, a PRD, or another clarified requirement artifact already exists. - The work is too large for one ticket but still needs strong coordination.
- The project would benefit from explicit blocking edges or parent-child relationships.
- You want to create milestone or integration gates instead of pushing all validation to the very end.
Do Not Use
- The change is small enough to fit inside one well-scoped ticket.
- The requirements are still ambiguous; clarify them first.
- The plan is already broken down into tickets with clear dependencies and acceptance criteria.
OpenASE Grounding
Design the breakdown around the platform that already exists:
- Use parent-child ticket relationships for hierarchy.
- Use
blocksdependencies only for true execution blockers. - Assume the scheduler may dispatch unrelated tickets in parallel when no blocking edge exists.
- Treat workflow pickup and finish statuses as real stage boundaries; do not advance a ticket unless its deliverable is genuinely ready for the next lane.
The goal is not to create the most tickets. The goal is to create the smallest graph that still preserves correctness, evidence, and throughput.
Core Principles
- Break down by deliverable, not by chore.
- A ticket should represent a meaningful output, not a vague activity.
- Avoid tickets like "research X", "prepare Y", or "adjust Z" unless the deliverable is explicit and reviewable.
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 · 174 lines · 23 tokens per session scan A 56199b2afbb1
task-breakdown is a skill published in the GitHub repository PacificStudio/openase (269 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,483 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 2026-08-30.
Other skills, from other repositories
aisee:init
A project setup and audit helper for OpenSpec, a system for planning and tracking software changes, in Aisee projects.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
omh-research-department
This is a Hermes-native research-department workflow skill.
omh-agent-board
This is a Hermes-native agent-board workflow skill.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.