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 kakutixyz-ai/agent-publishing-skills --skill adapter-technical-bloggit clone --depth 1 https://github.com/kakutixyz-ai/agent-publishing-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/kakutixyz-ai/agent-publishing-skills/adapter-technical-blog)<a href="https://agentmods.dev/skills/kakutixyz-ai/agent-publishing-skills/adapter-technical-blog"><img src="https://agentmods.dev/badge/skills/kakutixyz-ai/agent-publishing-skills/adapter-technical-blog/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/kakutixyz-ai/agent-publishing-skills/adapter-technical-blog"><img src="https://agentmods.dev/badge/skills/kakutixyz-ai/agent-publishing-skills/adapter-technical-blog.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 | $0.00026 | $0.00674 |
| Opus 5.5 | $0.00010 | $0.00270 |
| Sonnet 5.5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
adapter-technical-blog 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 2mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Blog Adapter
Use this adapter for platforms such as DEV Community, Hashnode, Medium, Zenn, Qiita, CSDN, 掘金, freeCodeCamp, CSS-Tricks, and similar article-first developer communities when no dedicated adapter is required.
Data Source Constraint
No internet search. All content must be generated from local sources only: the project brief, knowledge base, schemas, templates, and user-provided materials. Do not fetch or search external URLs.
Inputs
- A base draft matching
schemas/platform-draft.schema.json. - One platform profile from
knowledge/platforms/. knowledge/styles/technical-blog.md.- Optional template from
templates/base/article.mdortemplates/base/tutorial.md.
Process
- Extract a platform constraint sheet from the profile before writing:
- required language and regional variant;
- expected length or density cues, such as short forum answer, concise article, long-form tutorial, deep essay, or documentation-style reference;
- accepted content shape, such as tutorial, case study, implementation note, product story, support answer, or research summary;
- required tone, such as pedagogical, skeptical, formal, conversational, literary, founder-led, or purely technical;
- formatting rules for headings, code blocks, callouts, images, tags, links, and metadata;
- poor-fit and banned patterns.
- If the platform profile conflicts with the generic technical-blog pattern, the platform profile wins. For example, do not turn a concise support/community format into a long tutorial, and do not turn an essay platform into a code-heavy walkthrough.
- Match the target platform language from its platform profile. Do not translate into English by default when the profile requires Japanese, Chinese, Portuguese, Korean, Arabic, Spanish, German, or another primary language.
- Reframe the draft as knowledge sharing rather than promotion.
- Choose the article length from the profile:
- short-form platforms: write only the requested concise answer, blurb, or summary;
- tutorial platforms: provide reproducible steps, prerequisites, code, and expected results;
- long-form editorial platforms: build an argument with context, evidence, and trade-offs;
- educational platforms: explain why each step matters and avoid unexplained jumps.
- State the problem and target reader early using the platform's preferred style.
- Add environment, setup, code, screenshots, diagrams, or reproducible steps only when the platform expects them and the brief provides the facts.
- Follow the platform's heading, code block, and callout conventions exactly.
- Remove unsupported claims, generic marketing language, and content types listed as poor fit.
- End with the platform-appropriate close: summary, references, next step, or specific technical feedback request. Do not add a sales pitch unless the profile explicitly expects a CTA.
- Put a short
metadata.platform_constraints_appliedchecklist in the output covering language, length, tone, structure, and formatting.
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.
- 2mo ago First seen · 48 lines · 26 tokens per session scan A a181f4d9c268
adapter-technical-blog is a skill published in the GitHub repository kakutixyz-ai/agent-publishing-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 674 once invoked, about $0.0001 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.
adapter-technical-blog compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adapter-technical-blogkakutixyz-ai/agent-publishing-skills | Skill | 2 | 5mo ago | MIT | A | 26 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |