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.
git 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-client-report)<a href="https://agentmods.dev/rules/marker-io/mcp-skills/marker-client-report"><img src="https://agentmods.dev/badge/rules/marker-io/mcp-skills/marker-client-report/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/rules/marker-io/mcp-skills/marker-client-report"><img src="https://agentmods.dev/badge/rules/marker-io/mcp-skills/marker-client-report.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 | $0.00067 | $0.01268 |
| Opus 5.5 | $0.00027 | $0.00507 |
| Sonnet 5.5 | $0.00013 | $0.00254 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
marker-client-report 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
marker-client-report
Produce a polished, client-facing recap of what an agency completed on a website over a week or month, straight from Marker.io — grouped by page, written in plain language, ready to paste into an email or send as-is. Read-only.
When to use
"Write the weekly report for <client>", "what did we ship for <project> this month", "monthly recap
for the <site> work", "client status update from Marker". For analyzing recurring patterns rather than
reporting a period's work, use marker-insights; for triaging the open backlog, use marker-triage.
Inputs to confirm
- Which project (one client / site is usually one project; resolve per the operating rules).
- The window: default the last 7 days, or "last month" / last 30 days / an explicit date range.
- Whether to include sections beyond completed work: in-progress now, and newly reported this period. Default: completed only.
Steps
- Resolve the project and read
project_getfor its name andwebsiteUrls(the report header and the page mapping). - Decide which statuses count as completed —
ResolvedandClosedby default. Statuses are project-specific and can be renamed, so don't assume a customized board uses the English defaults: confirm which are in use by probingissues_listwith eachstatusvalue, and if it is unclear which statuses mean "done", show the candidates and ask. - Pull issues with
issues_list, paginatinglimit/offsetfully. Keep fields lean:markerId,title,status,url,createdAt,updatedAt. The MCP has no date filter, so window client-side: an item counts as completed this period when its status is one of the completed states and itsupdatedAtfalls in the window. - Classify each completed item as a content update (typo, copy, wrong number or fact, image, link,
layout) or a fix (functional bug). Marker does not expose an issue's type to read, so infer it
from the title and page URL; open
issue_get/issue_get_screenshotonly when the title is too thin to describe in client terms. - Group by page (from the URL relative to
websiteUrls), and within a page by content vs fix. - Write the report (see Output). Translate internal titles into client language: "Fix typo in intro paragraph" becomes "Corrected a typo in the Solutions page intro". Drop Marker jargon, statuses, and IDs from the client-facing copy.
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 · 88 lines · 67 tokens per session scan A aeded9303331
marker-client-report is a cursor rule published in the GitHub repository marker-io/mcp-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,268 once invoked, about $0.0003 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 cursor rules, from other repositories
write-issue
Turn a rough idea into a well-structured GitLab issue with clear problem statement, root cause, and testable acceptance criteria.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.