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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.01693 |
| Opus 5.5 | $0.00021 | $0.00677 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,693 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…