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 rules/marker-io/mcp-skills/marker-syncgit clone --depth 1 https://github.com/marker-io/mcp-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/rules/marker-io/mcp-skills/marker-sync)<a href="https://agentmods.dev/rules/marker-io/mcp-skills/marker-sync"><img src="https://agentmods.dev/badge/rules/marker-io/mcp-skills/marker-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 | $0.00061 | $0.00890 |
| Opus 5 | $0.00030 | $0.00445 |
| Sonnet 5 | $0.00012 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
marker-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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
marker-sync
Keep Marker.io and an external tracker (GitHub Issues, Linear, Jira) consistent: full diagnostic context flows into the tracker, resolution flows back to Marker. Eliminates the "closed in the tracker, still open in Marker.io" mismatch.
When to use
"Pull new marker issues into <tracker>", "enrich these tickets with marker context", "mark the done ones ready to test in github and resolved in marker", "are marker and linear out of sync".
Prerequisites
A connected tracker. Use whatever the user has: GitHub via the gh CLI, Linear via mcp__linear__*,
Jira via its MCP/CLI. If none is connected, say so and stop.
Matching issues across systems
Match a Marker.io issue to its tracker item by, in order: an explicit Marker link/ID in the tracker item, the issue URL, then a close title match. When unsure, list the candidate pairs and ask.
Steps
- Pull new/updated Marker.io issues (
issues_list, recent window). Pull the corresponding tracker items in one pass. - Enrich thin tracker items: for any tracker ticket missing diagnostic context, add the Marker
screenshot link, console errors, failing network requests, and browser/OS from
issue_get_context(plus drill-downs). Propose the edit before writing to the tracker. - Reconcile status both ways. Build a table of every pair and its two statuses. Flag mismatches (resolved on one side, open on the other).
- On close: when a fix has landed, set the tracker state (e.g. "Ready to Test") and the Marker.io
status to its resolved equivalent (
issue_update_status, discovered viaproject_get), and document the root cause + fix as a comment on both sides (comment_createon Marker).
Gating
Every write (tracker edits, Marker status changes, comments) is proposed as a table first and applied only after confirmation. Never close an issue on one side without updating the other.
Operating rules
This skill drives the Marker.io MCP. Read tools: projects_list, project_get, project_list_users,
list_issue_types, issues_list, issue_get, issue_get_context, issue_get_screenshot,
issue_get_attachments, issue_get_console_log, issue_get_network_request. Write tools:
issue_update_status, issue_update_assignee, issue_update_priority, issue_update_type,
comment_create.
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 · 66 lines · 61 tokens per session scan A 75526a156e04
marker-sync is a cursor rule published in the GitHub repository marker-io/mcp-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 890 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 cursor rules, from other repositories
api
USE WHEN: Defining HTTP requests, endpoints, and handling API responses.
ui-components
USE WHEN: Building UI components, structuring layouts, and applying styles using Tailwind CSS.
core-principles
USE WHEN: Applying core principles and enforcing global project constraints.
tanstack-query
USE WHEN: Managing server state, fetching data, and handling mutations with TanStack Query.
state-management
USE WHEN: Managing global client state with Zustand and handling client-side state logic.
typescript
USE WHEN: Defining TypeScript types, Zod schemas, and generic constraints for type safety.