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 marker-io/mcp-skills --skill marker-triagegit 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/skills/marker-io/mcp-skills/marker-triage)<a href="https://agentmods.dev/skills/marker-io/mcp-skills/marker-triage"><img src="https://agentmods.dev/badge/skills/marker-io/mcp-skills/marker-triage/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/marker-io/mcp-skills/marker-triage"><img src="https://agentmods.dev/badge/skills/marker-io/mcp-skills/marker-triage.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 | $0.00090 | $0.01342 |
| Opus 5 | $0.00045 | $0.00671 |
| Sonnet 5 | $0.00018 | $0.00268 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
marker-triage 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 11d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
marker-triage
Turn a Marker.io feedback backlog into decisions: content split from bugs, grouped by page, prioritized, deduplicated, with the affected users listed. Built for agencies and website teams, where most feedback is content (typos, copy, images, links) and the rest is functional bugs. Takes a backlog of 100+ reports to a decision-ready triage in minutes.
When to use
The user wants to make sense of many Marker.io issues at once: "go through the <project> feedback and
categorize it", "what are the top issues this week", "triage the backlog", "which bugs hit the most
users". For fixing a single report in code, use marker-bug-to-fix instead.
Inputs to confirm
- Which project (resolve per the operating rules).
- Scope: default to issues from the last 14 days, or "all" if asked. Confirm before pulling a large board.
- Whether to write triage decisions back (priority/type/status) or just produce the report.
Steps
- Resolve the project and discover its issue types and statuses (
list_issue_types,project_get). Read the site'swebsiteUrlsso each issue URL maps to a page. - Pull the backlog with
issues_list, paginatinglimit/offsetuntil the scope is covered. The MCP has no date filter, so paginate fully and filter to the window client-side oncreatedAt. Usefieldsto keep the list lean (markerId, title, status, priority, url, reporter, createdAt). - Split every report into content (typo, copy/wording, wrong number or fact, image/media, broken
link, layout/spacing, translation) or functional (form, navigation, JavaScript error, responsive
break, performance). Marker does not expose an issue's type to read, so infer it from the title and
page URL; enrich with
issue_get+issue_get_context, aissue_get_screenshot, or a specificissue_get_console_log/issue_get_network_requestonly when it changes the call. - Group by page (from the URL), then by theme within each page. Merge near-duplicate themes.
- Rate criticality per issue (blocker / high / medium / low) from impact and breadth, not the reporter's wording. Weigh page prominence: a typo on the homepage is low-severity but high-visibility. Note the reasoning briefly.
- Flag quick wins: content fixes that are likely a two-minute change (a typo, a wrong number, a swapped image). Agencies clear these fast to show clients immediate progress.
- Detect duplicates and repeat reporters: group issues sharing a page + theme or near-identical screenshots; flag reporters who filed multiple related issues.
- Surface blind spots: systemic patterns spanning pages (one root cause behind many reports, e.g. a stale data source repeated across the site).
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.
- 11d ago First seen · 87 lines · 90 tokens per session scan A d7724ce9d735
marker-triage is a skill published in the GitHub repository marker-io/mcp-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,342 once invoked, about $0.0005 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
meeting-notes-to-tasks
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
task-decomposition
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.