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/mrtblount/spec-to-ship/syncnpx skills add mrtblount/Spec-to-Ship --skill syncgit clone --depth 1 https://github.com/mrtblount/Spec-to-ShipWrote 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/mrtblount/spec-to-ship/sync)<a href="https://agentmods.dev/skills/mrtblount/spec-to-ship/sync"><img src="https://agentmods.dev/badge/skills/mrtblount/spec-to-ship/sync.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 | $0.00052 | $0.01693 |
| Opus 5 | $0.00026 | $0.00847 |
| Sonnet 5 | $0.00010 | $0.00339 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
sync 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool availability:
- GitHub CLI (
gh) for creating projects and issues - Linear MCP (
mcp__claude_ai_Linear__*) for creating Linear documents and issues - Both support programmatic creation and updates
Sync architecture:
SPEC.md ──────→ Linear Document (PRD / Initiative)
TASKS.md ─────→ GitHub Issues ←──→ Linear Issues (bidirectional)
↕
GitHub Project Board
Linear has a native GitHub integration that handles bidirectional sync between GitHub Issues and Linear Issues. We don't need to build that — just configure it.
Also: Does a GitHub Project or Linear project already exist for this, or should I create new ones?"
AWAIT: User choice STORE: sync_targets, existing_project_ids
</step>
<step id="2" name="GitHub Projects Setup">
IF sync_targets includes GITHUB:
IF existing GitHub Project: VERIFY: Project exists and is accessible USE: existing project ID ELSE: CREATE project: gh project create --title "{Project Name}" --owner {user/org}
FOR each task in TASKS.md:
CREATE GitHub Issue:
gh issue create
--title "T{NNN}: {task title}"
--body "{task description with validation criteria}"
--label "{layer}"
--project "{project name}"
MAP dependencies:
- Add "Depends on #X" in issue body for each dependency
- Add labels for layer (foundation, core, feature, integration, polish)
- Add labels for complexity (low, medium, high)
ORGANIZE project board: - Create columns/status fields: Backlog, Ready, In Progress, Review, Done - Place foundation tasks in "Ready" - Place dependent tasks in "Backlog" - Add priority field matching task execution order
REPORT: "Created {count} issues in GitHub Project: {project_url} Board organized by execution order with dependency tracking."
</step>
<step id="3" name="Linear Setup">
IF sync_targets includes LINEAR:
DETERMINE Linear team: Use mcp__claude_ai_Linear__list_teams to find available teams ASK user which team if multiple exist
CREATE Linear document from SPEC.md: Use mcp__claude_ai_Linear__create_document with: - Title: "{Project Name} — Product Specification" - Content: Contents of SPEC.md (converted to Linear-compatible format)
IF sync_targets is LINEAR_ONLY (no GitHub): FOR each task in TASKS.md: CREATE Linear issue: Use mcp__claude_ai_Linear__save_issue with: - Title: "T{NNN}: {task title}" - Description: task description + validation criteria - Priority: based on layer (foundation=urgent, core=high, feature=medium, polish=low) - Labels: layer name, complexity
REPORT: "Created SPEC.md as Linear document: {doc_url} {count} issues created in Linear project."
</step>
<step id="4" name="Bidirectional Sync Setup (GitHub ↔ Linear)">
IF sync_targets includes BOTH GitHub AND Linear:
EXPLAIN to user: "## Setting Up GitHub ↔ Linear Sync
Linear has a native GitHub integration that handles bidirectional sync.
Here's what to do:
**One-time setup (takes ~2 minutes):**
1. Go to Linear → Settings → Integrations → GitHub
2. Connect your GitHub account/organization
3. Select the repository for {project_name}
4. Configure sync settings:
- ✅ Sync issues bidirectionally
- ✅ Auto-create Linear issues from GitHub issues
- ✅ Sync status changes (closing a GitHub issue closes the Linear issue)
- ✅ Sync comments
- ✅ Sync labels
**How it works after setup:**
- Issues created in GitHub → automatically appear in Linear
- Status changes in either tool → synced to the other
- Comments on GitHub issues → appear in Linear and vice versa
- Closing an issue in either place → closes it in both
**What this means for your workflow:**
- Claude Code updates GitHub Issues via `gh` CLI as tasks complete
- Those updates automatically flow to Linear
- You or collaborators can manage priorities in Linear's UI
- The senior dev in your accelerator can watch progress in Linear
Would you like me to walk you through the setup now, or do you want
to handle it later?"
IF user wants walkthrough now: Use browser automation tools to guide through Linear settings OR provide step-by-step with screenshots via Linear's docs
AWAIT: User confirms sync is configured
</step>
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 · 204 lines · 52 tokens per session scan A 293aaa140a7f
sync is a skill published in the GitHub repository mrtblount/Spec-to-Ship (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,693 once invoked, about $0.0003 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.
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.
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.
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.
simulator-reactions
Simulator.Company reactions specialist — comments, events, approvals, ratings and other feedback attached under an actor. Use when the user wants to comment on an actor, reply in a thread, read/like/pin the discussion, mark comments read, or get reaction stats. Activate when the user says "comment on this actor"…