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/stephenqiu30/stephen-claude/linear-tasknpx skills add StephenQiu30/stephen-claude --skill linear-taskgit clone --depth 1 https://github.com/StephenQiu30/stephen-claudeWrote 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/stephenqiu30/stephen-claude/linear-task)<a href="https://agentmods.dev/skills/stephenqiu30/stephen-claude/linear-task"><img src="https://agentmods.dev/badge/skills/stephenqiu30/stephen-claude/linear-task.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 5.1 | $0.00091 | $0.01553 |
| Opus 5 | $0.00046 | $0.00776 |
| Sonnet 5 | $0.00018 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
linear-task 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 5d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Linear task
Create issues that an implementation agent and reviewer can execute without guessing. Preserve facts from the request and repository; never manufacture requirements, evidence, commands, labels, IDs, or dependencies.
Mutation boundary
- Create an issue only when the user explicitly asks to create or submit it.
- When asked to draft, rewrite, review, or improve an issue, return or apply the requested text without creating a second issue.
- Update an existing issue only when the request authorizes that update.
- Ask one focused question before mutation only when a required choice cannot be inferred safely and would materially change scope, ownership, routing, or acceptance. Otherwise proceed with documented assumptions.
Workflow
- Read the request, linked requirements/designs/plans, repository instructions, and relevant existing issues. Separate confirmed facts from assumptions.
- Define one independently deliverable outcome. If the request contains multiple outcomes that can ship or fail independently, propose or create separate issues and express their relationships.
- Search the same team/project for open issues with matching component, behavior, error text, or outcome. Do not create a duplicate. Report the existing issue or, when authorized, improve it instead.
- Resolve required metadata from project conventions and nearby issues: team, project, state, priority when specified, labels, parent/related issues, and blocking relationships.
- Draft the title and body using the contract below. Remove empty optional sections and every placeholder before mutation.
- Run the quality gate. Create or update the issue only when it passes.
- Re-read the saved issue and verify title, rendered body, state, project, labels, and relationships. Repair partial writes when authorized; otherwise report the exact mismatch and do not claim completion.
- Return the issue identifier, title, URL, state, labels, and relationships.
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.
- 5d ago First seen · 168 lines · 91 tokens per session scan A 31e4db1f6d1d
linear-task is a skill published in the GitHub repository StephenQiu30/stephen-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,553 once invoked, about $0.0005 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
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
peer-selection
当用户纠结交朋友/选伴侣/换圈子、感觉被周围人拖累、问「该不该疏远某人」时调用。 核心理念: 五只黑猩猩理论(你的行为由最常接触的5人预测); 同伴是主动选择而非巧合; 只与价值观一致者深交, 远离愤世嫉俗者/愤怒者。 不适用于: 职场必须共事的同事关系(可先设边界)。 Triggers: 朋友/圈子/伴侣/该不该疏远/被拖累/五只黑猩猩/peer/friends/circle/values.
dependency-triage
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
draft-release-notes
Turn changelog-scan output into polished, categorized release notes draft. Propose only.
use-sdk
Install, configure, and use a TypeScript SDK generated with @ama-sdk. Use when user wants to call APIs, set up a client (fetch, Angular, beacon), or understand how to use an existing SDK package.