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/tx1207/hello-scholar/generating-tasksnpx skills add Tx1207/hello-scholar --skill generating-tasksgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/generating-tasks)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/generating-tasks"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/generating-tasks.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 | $0.00047 | $0.02476 |
| Opus 5 | $0.00023 | $0.01238 |
| Sonnet 5 | $0.00009 | $0.00495 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
generating-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 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating Tasks
Turn the current approved Plan into an execution contract. Preserve decisions already made upstream; return missing design to the Spec or Plan instead of deciding it inside Tasks.
A top-level Task is a tracer task: the smallest dependency-complete slice that advances one observable Plan outcome, fits a fresh context, and leaves the repository independently verifiable. Its Work section contains concrete 2–5 minute actions.
1. Establish the contract
- Locate the target Spec Bundle. Read
spec.mdin full, then readplan.mdin full. Read relevant Architecture, source, tests, configuration, or persisted formats only to confirm facts the Plan already depends on. - Run
docs checkwithhello-scholar. Continue when the Spec isaccepted, the Plan isapproved, andplan.spec_revisionequals the current Specrevision. - Build an obligation ledger covering every Spec acceptance criterion and every Plan requirement: scope, files, interfaces, phases, tests or experiments, migration, cleanup, rollback,
Must Not Touch, and Tasks-generation rules.
If a material choice remains open or the documents conflict, leave tasks.md unchanged and name the exact decision that belongs in the Spec or Plan.
Complete this step when: every accepted requirement has one ledger entry, all paths and commands needed for decomposition are grounded in project facts, and no Task would need to invent design.
2. Draft tracer tasks
Default to vertical, behavior-bearing slices. A tracer task may cross test, source, configuration, and documentation files when those edits together produce one independently checkable outcome.
A horizontal slice such as “write all tests,” “change the data layer,” or “update documentation” is not a Task unless the approved Plan makes that layer an independently valuable and verifiable deliverable. Keep an indivisible repository change together; split a Task when it contains more than one outcome, cannot fit a fresh context, or cannot be validated on its own.
What ships with it
3 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.
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 · 133 lines · 47 tokens per session scan A 001480e0c87c
generating-tasks is a skill published in the GitHub repository Tx1207/hello-scholar (5 stars, last pushed 22d ago), licensed MIT. It adds 47 tokens to every session and 2,476 once invoked, about $0.0002 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
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.
okx-task-watch
监听任务进展 / 帮我盯着任务 / 任务有动静告诉我 / 历史消息 / 未读消息 / 未决策 / 待决策 / 继续监听 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A user-session task-notification monitor: live long-poll via okx-a2a user watch (also drains backlog of past/missed/unread events on entry) plus…
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.