Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. 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/greenmtnsun/GitEasy/main/.claude/skills/blog-content-pipeline/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/blog-content-pipeline)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/blog-content-pipeline"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/blog-content-pipeline/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/greenmtnsun/giteasy/blog-content-pipeline"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/blog-content-pipeline.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 | $0.00148 | $0.01935 |
| Opus 5.5 | $0.00059 | $0.00774 |
| Sonnet 5.5 | $0.00030 | $0.00387 |
| Haiku 4.5 | $0.00015 | $0.00194 |
Grade A, and why
blog-content-pipeline 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 today.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
editorial-stanceandfeedback_wikiengine_anti_vibefor the never-fabricate rule this pipeline enforces mechanically.blog-proposalfor drafting a brand-new post (this skill audits/heals it once drafted).feedback_deploy_requires_explicit_go— this pipeline never publishes; it only produces a pass/hold report.
Blog content pipeline
Why this exists
Keith's blog work (KeithsWebsite / keith-ramsey.com, PesterForge's Pester-for-Beginners series, and future project blogs) has repeatedly shipped with broken links, missing images, and fabricated claims that only surfaced after Keith caught them live. This pipeline moves that catch earlier and makes it mechanical instead of relying on a human proofread every time.
It is a two-layer system:
- Deterministic layer —
tools/Test-BlogContent.ps1(per-repo copy; the reference implementation lives atC:\Sysadmin\KeithsWebsite\tools\Test-BlogContent.ps1). Crawls every link and image reference and reports real HTTP/file-system ground truth; extracts every fenced code block and actually executes it (PowerShell, PesterDescribe/Itblocks viaInvoke-Pester, Python, Bash) in an isolated temp directory, never against Keith's real filesystem state. Never invents a verdict — everything is a real HTTP status, a real decoded image, or a real execution result. - Judgment layer — you (Claude), reading the checker's JSON output plus the full post. This is where fabrication-checking, voice-scoring, and "was that error intended" calls happen — things a regex genuinely cannot decide.
Step-by-step
0. Confirm the target before running anything. State the repo, the -ContentPath, and the -RepoRoot you're about to point the checker at. If a project's content directory or static-site structure isn't already known (route resolution in the script assumes a Next.js src/app layout — a true Hugo/Jekyll/Docusaurus project needs its own route-discovery logic), say so and adapt or ask rather than guessing blindly. Don't assume "the Hugo blog" means any specific repo — verify the path exists first.
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.
- today First seen · 64 lines · 148 tokens per session scan A 7b3539d6ff4d
blog-content-pipeline is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 148 tokens to every session and 1,935 once invoked, about $0.0006 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 2026-11-18.
blog-content-pipeline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog-content-pipelinegreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 148 | Claude Code |
| create-verification-skillYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 45 | Claude Code |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | 2d ago | MIT | A | 104 | Claude Code |
| eval-dataset-designbojieli/ai-agent-book | Skill | 59k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.4k | today | MIT | A | 55 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |