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/jmanhype/speckit/speckit.linear.importgit clone --depth 1 https://github.com/jmanhype/speckitWrote 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/jmanhype/speckit/speckit.linear.import)<a href="https://agentmods.dev/commands/jmanhype/speckit/speckit.linear.import"><img src="https://agentmods.dev/badge/commands/jmanhype/speckit/speckit.linear.import.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 | $0.00760 |
| Opus 5 | $0.00006 | $0.00380 |
| Sonnet 5 | $0.00002 | $0.00152 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
speckit.linear.import 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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
-
Parse the Linear issue reference from user input:
- Accept formats:
LINEAR-123,TEAM-123,https://linear.app/team/issue/TEAM-123, or issue title search - If no input provided, ask: "Which Linear issue should I import? (e.g., TEAM-123 or search term)"
- Accept formats:
-
Fetch the issue from Linear using MCP:
- Use
mcp__linear__search_issueswith the issue identifier or search query - Extract: title, description, priority, labels, assignee, status, comments
- If multiple results, show list and ask user to select
- Use
-
Determine feature number:
- Check existing
specs/directory for highest numbered feature - Increment to get next feature number (e.g.,
002if001exists)
- Check existing
-
Create feature directory:
mkdir -p specs/[NUMBER]-[SLUG]/- Generate slug from issue title (lowercase, hyphens, max 50 chars)
- Example:
specs/002-user-authentication/
-
Generate spec.md from Linear issue:
- Use the spec template from
.specify/templates/spec-template.md - Map Linear fields to spec sections:
Linear Field Spec Section Title Feature title Description Overview / User Stories Priority Priority (P1/P2/P3) Labels Tags/Categories Comments Additional context in Notes - Use the spec template from
-
Add Linear tracking metadata to spec header:
--- linear_id: TEAM-123 linear_url: https://linear.app/team/issue/TEAM-123 imported_at: 2025-01-15T10:30:00Z sync_status: imported --- -
Create bidirectional link:
- Add comment to Linear issue (using
mcp__linear__add_comment):📋 Spec Kit: Feature specification created Path: specs/[NUMBER]-[SLUG]/spec.md
- Add comment to Linear issue (using
-
Output summary:
✅ Imported LINEAR-123 → specs/002-user-authentication/ Linear Issue: [Title] Spec Path: specs/002-user-authentication/spec.md Priority: P1 Next steps: - Run /speckit.clarify to resolve any ambiguities - Run /speckit.plan when ready for technical planning
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.
- 2d ago First seen · 91 lines · 12 tokens per session scan A 2ac6c634b166
speckit.linear.import is a command published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 760 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 2026-09-01.
Other commands, from other repositories
paul:add-phase
Add a new phase to current milestone.
paul:discuss-milestone
Explore and articulate next milestone vision.
paul:discuss
Explore and articulate phase vision before planning.
paul:remove-phase
Remove a future (not started) phase.
flow-archive
Run the canonical flow/archive Flow lifecycle.
flow-cleanup
Run the canonical flow/cleanup Flow lifecycle.