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 commands/kellykampen/agent-skills/interview-lineargit clone --depth 1 https://github.com/kellykampen/agent-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/commands/kellykampen/agent-skills/interview-linear)<a href="https://agentmods.dev/commands/kellykampen/agent-skills/interview-linear"><img src="https://agentmods.dev/badge/commands/kellykampen/agent-skills/interview-linear.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 | $0.00012 | $0.00571 |
| Opus 5 | $0.00006 | $0.00285 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
interview-linear 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.
What it actually says
Read this comment $1 and interview me in detail using the AskUserQuestionTool about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions are not obvious.
If you are in a git repo, then be sure to check the current codebase and ask relevante questions, as this is likely a feature or refacotor of the current codebase.
Be very in-depth and continue interviewing me continually until it’s complete, then use the linear-cli skills to create a project, with issues with in the repo team (the team is usually similiar named to the repo). the linear project should be the what, why, how and key features. Each issue should be no larger than 3 points of effort. If you have an issue that larger, you need to break it down. Be sure to link issues with blockers/dependencies.
Also link PROJECT-level dependencies. After the project exists, check the team's other projects and link the ones this new project depends on (projectRelationCreate via linear-cli api mutate — the Linear MCP and linear-cli rel only do issue relations, not project↔project). Nearly every project depends on at least one other; only a genuinely foundational project is a legitimate solo. Orientation is load-bearing: type: "dependency", prerequisite anchored end, dependent anchored start ({ projectId: <prereq>, anchorType: "end", relatedProjectId: <this project>, relatedAnchorType: "start" }). The reverse anchor order (start→end) silently fails to render in the roadmap/Dependencies column.
Each issue MUST have detailed acceptance criteria written as markdown checkboxes — one - [ ] per criterion, never plain bullets (-/*), a numbered list, or prose. The format is load-bearing: Linear renders - [ ] as tickable checkboxes, and bullet AC can't be checked off, so it can't be verified or closed out. One observable, testable assertion per box.
Definition of Done (enforce this, always): an issue is NOT Done until every acceptance-criteria checkbox is checked. And a checkbox may ONLY be checked after an independent agent has verified that specific criterion against the actual codebase (via the linear-ac-verification skill or an independent reviewer that ran the real tests/build) — never self-checked, never checked on a claim. Moving an issue to Done with unchecked or bullet-point AC is a defect: the issue is not done. Use linear-ac-verification before closing anything.
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 · 18 lines · 12 tokens per session scan A 8b0ed3f44bb0
interview-linear is a command published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 571 once invoked, about $0.0001 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 commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
clarify
Walk through inbox items applying the GTD decision tree. Usage: /gtd:clarify [--id gtd-xxx].