Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hxy91819/mason-skillsnpx agentmods add skills/hxy91819/mason-skills/publishWrote 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/hxy91819/mason-skills/publish)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/publish"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/publish/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/hxy91819/mason-skills/publish"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/publish.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 | $0.00132 | $0.02511 |
| Opus 5.5 | $0.00053 | $0.01004 |
| Sonnet 5.5 | $0.00026 | $0.00502 |
| Haiku 4.5 | $0.00013 | $0.00251 |
Grade A, and why
article-workflow-publish 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 1mo 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Workflow Publish
这是流程类 Skill,默认仅在用户显式调用 $article-workflow-publish 时运行。
This is Phase 8 of the article-workflow-* series, corresponding to "Channel Publishing & Syncing" in the article optimization workflow.
Goal: Sync the author-maintained 06-final-review/final.md into channel drafts. Image URLs are managed via 08-publish/image-map.json; text remains fully consistent with the source. Scripts handle mechanical substitution; the skill invokes the LLM to find "adaptations needed beyond images, per-channel" and reports them (report only, no modifications).
Trigger Scenarios
Use this skill when the user asks to:
- Sync
final.mdto internal wiki / WeChat Official Account / Zhihu, etc. - Regenerate
08-publish/<channel>/<channel>-meta.mdand<channel>-body.md - Run reverse extraction (first-time sync when the author exports an already-published draft with embedded images from the channel editor)
- Check sync status between channel drafts and the source
- Validate that
image-map.jsonis complete - Add a new channel (
wechat/zhihu, etc.)
Inputs & Outputs
Default inputs:
.article-workflow/06-final-review/final.md(source).article-workflow/08-publish/image-map.json(mapping)- Optional:
.article-workflow/08-publish/<channel>/<channel>-published.md(for first-time reverse extraction)
Default outputs:
.article-workflow/08-publish/<channel>/<channel>-meta.md(title + lead paragraph; maintained independently for the internal wiki channel).article-workflow/08-publish/<channel>/<channel>-body.md(body text, excluding title and lead).article-workflow/08-publish/<channel>/<channel>.lint.json(machine-level lint output)- Skill output: LLM report (printed in conversation, not written to a file)
Additional outputs on first-time image pasting (sync --templated):
.article-workflow/08-publish/<channel>/<channel>-templated.md(full draft preservingimgs/xxxpaths).article-workflow/08-publish/<channel>/<channel>-meta-templated.md(title + lead, preservingimgs/xxx).article-workflow/08-publish/<channel>/<channel>-body-templated.md(body text, preservingimgs/xxx)
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.
- 1mo ago Changed · +2 lines 837983aa8fc9
- 2mo ago Changed · +3 lines · +132 tokens per session b5219be75cb2
- 2mo ago First seen · 196 lines · 0 tokens per session scan A 0c68c1385b08
article-workflow-publish is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 2,511 once invoked, about $0.0005 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.
article-workflow-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| article-workflow-publishhxy91819/mason-skills | Skill | 3 | today | MIT | A | 132 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |