Borrowing it
Nothing to install: this file belongs to BlogFactoryHQ/ghost-publisher-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BlogFactoryHQ/ghost-publisher-mcp/main/.agents/skills/ghost-editorial-batch/SKILL.mdgit clone --depth 1 https://github.com/BlogFactoryHQ/ghost-publisher-mcpWrote 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/blogfactoryhq/ghost-publisher-mcp/ghost-editorial-batch)<a href="https://agentmods.dev/skills/blogfactoryhq/ghost-publisher-mcp/ghost-editorial-batch"><img src="https://agentmods.dev/badge/skills/blogfactoryhq/ghost-publisher-mcp/ghost-editorial-batch/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/blogfactoryhq/ghost-publisher-mcp/ghost-editorial-batch"><img src="https://agentmods.dev/badge/skills/blogfactoryhq/ghost-publisher-mcp/ghost-editorial-batch.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 | $0.00064 | $0.00988 |
| Opus 5 | $0.00032 | $0.00494 |
| Sonnet 5 | $0.00013 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
ghost-editorial-batch 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ghost Editorial Batch
Use Ghost Publisher as the CMS safety boundary. The host AI may research, evaluate sources, and draft text with its own capabilities; never add a search provider, scraper, model key, or quality score to the MCP workflow.
Workflow
- Call
check_connection. Confirm the permission profile and whether headless live checking is configured. Stop if the required write capability is absent. - Resolve no more than 25 exact targets in the user-supplied order. Call
get_postorget_pagefor every target and retain each ID plusupdated_at. - Call
audit_content. Report only its mechanical signals; do not infer accuracy, quality, source reliability, or link health. If the user asks about content or publication risk, use the reporting rules below. - Prepare the smallest applicable change operation:
update_fieldsfor metadata and named fields.append_sectionorprepend_sectionto add a Markdown section while preserving existing Lexical children.replace_exact_textonly for one exact, unique text node.replace_bodyonly when the user explicitly approves complete body replacement and the preview allows it.
- Call
preview_changes. Show every full before snapshot, changed field, character and node effect, protected/removed node, warning, required scope, and preview hash. A broad request such as “improve the content” is not body-replacement approval. - Stop for explicit approval of the exact unchanged batch and exact scopes. Do not combine this with scheduling approval.
- Call
apply_change_setonce with the unchanged changes, preview hash, exact scopes, anduser_confirmed: true. Do not retry a write automatically. - Inspect every receipt and Ghost readback. Report succeeded, failed, and not-attempted targets, revision requests, preserved fields, and any partial completion. Keep the returned before snapshots available to the user; the MCP stores none. Recovery uses Ghost Admin revision history or a separately previewed reverse change-set.
- If scheduling is requested, call
plan_schedulewith the exact applied/read-back revisions, ordered posts, local start time, IANA timezone, and interval hours. Show local times, exact UTC timestamps,newsletter: false, headless visibility, and the plan hash. When publication cadence is in scope, use a boundedlist_postsquery to report existing scheduled posts around that window. - Stop for separate schedule approval. Then call
schedule_postsonce with the unchanged posts, plan hash, anduser_confirmed: true. Never add newsletter/email parameters or trigger deployment for scheduling.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 46 lines · 64 tokens per session scan A 330b76baf832
ghost-editorial-batch is a skill published in the GitHub repository BlogFactoryHQ/ghost-publisher-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 64 tokens to every session and 988 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
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…