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 georgeguimaraes/claude-code-ghost --skill ghost-bloggit clone --depth 1 https://github.com/georgeguimaraes/claude-code-ghostWrote 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/georgeguimaraes/claude-code-ghost/ghost-blog)<a href="https://agentmods.dev/skills/georgeguimaraes/claude-code-ghost/ghost-blog"><img src="https://agentmods.dev/badge/skills/georgeguimaraes/claude-code-ghost/ghost-blog.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 5.1 | $0.00118 | $0.03623 |
| Opus 5 | $0.00059 | $0.01811 |
| Sonnet 5 | $0.00024 | $0.00725 |
| Haiku 4.5 | $0.00012 | $0.00362 |
Grade A, and why
ghost-blog scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ghost Blog Management
Interact with the user's Ghost blog using the Content API (read-only, public data) and Admin API (full read/write access).
Environment Variables
| Variable | Purpose |
|---|---|
GHOST_API_URL |
Base URL of the Ghost instance (e.g. https://myblog.ghost.io) |
GHOST_CONTENT_API_KEY |
Content API key for read-only public access |
GHOST_ADMIN_API_KEY |
Admin API key in {id}:{secret} format for full access |
These are created in Ghost Admin under Settings > Integrations > Custom Integration.
The ghost_api.py Module
All operations use the Ghost class from ghost_api.py (stdlib only, no dependencies). It handles JWT auth, JSON serialization, and HTTP requests. The module lives in the same directory as this skill file.
Every script follows this pattern (use the base directory shown when this skill is loaded as the PYTHONPATH):
PYTHONPATH=<base_directory_of_this_skill> python3 << 'PY'
from ghost_api import Ghost
g = Ghost()
# ... operations here ...
PY
API Methods
| Method | Signature | Description |
|---|---|---|
g.get(path, **params) |
Returns dict | GET request, params become query string |
g.post(path, data, **params) |
Returns dict | POST with JSON body |
g.put(path, data, **params) |
Returns dict | PUT with JSON body |
g.delete(path) |
Returns None | DELETE request |
g.upload(file_path, ref=None) |
Returns URL string | Multipart image upload |
g.unsplash_search(query, orientation="landscape", per_page=10) |
Returns list of dicts | Search Unsplash photos |
g.unsplash_caption(photo_id=None, user_name=None, user_username=None) |
Returns HTML string | Build Unsplash attribution caption |
g.set_unsplash_feature_image(post_id, photo_id) |
Returns post dict | Set feature image from Unsplash photo ID |
Path convention: paths start with content/ or admin/ (e.g. content/posts, admin/posts/abc123). Auth is handled automatically based on prefix.
What ships with it
2 files 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.
- 7d ago First seen · 381 lines · 118 tokens per session scan A 5afeadcc4617
ghost-blog is a skill published in the GitHub repository georgeguimaraes/claude-code-ghost (12 stars, last pushed 6mo ago), licensed MIT. It adds 118 tokens to every session and 3,623 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ecosystem-audit
ALWAYS use this skill when the user asks any question about their Claude Code setup, installed skills, memory system, lessons, feedbacks, handoffs, worktrees, ADRs, docs, or /.claude directory health. This is the go-to skill for introspection of the Claude Code environment itself. Specifically trigger on: (1) Skill…
claude-plugin-repo-ci-release
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (a repo with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator that runs on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever a VERSION file…
green-gate-never-examined-the-case
A check reported clean without examining the case it exists for — "green" meant "nothing ran". Use when about to trust a gate, test or CI step you have never watched fail; when a guard is green but the bug it guards shipped anyway; when a check passes on a shallow clone, a disabled object, a malformed input or an…
skill-portfolio-repo-placement-scan
Scan a portfolio of authored Claude Code skills and produce, per target repo, a precise list of which skills to ADD, which to UPDATE (with direction), and which to CROSS-LINK rather than copy. Uses a per-repo function-level inclusion bar, portfolio deduplication (never recommend a skill already homed as its own repo…
session-handoff
End-of-session handoff that captures session knowledge, dispatches output across the canonical 7-bucket docs/ taxonomy (decisions/runbooks/analysis/references/reviews/handoffs/deliverables — aligned with memory-hygiene v3.3), triggers a doc-freshness reverse-lint + skill-freshness audit to catch stale normative…
successor-handoff
Use when orchestrating long-running autonomous work — overnight runs, multi-hour research, multi-track experiments, 10+ hour jobs — where a single Claude context window cannot hold the full run. Establishes a lean parent orchestrator, file-first subagents, and successor-handoff (fresh subagent spawned mid-run when…