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 Kong/ai-marketplace --skill technical-writinggit clone --depth 1 https://github.com/Kong/ai-marketplaceWrote 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/kong/ai-marketplace/technical-writing)<a href="https://agentmods.dev/skills/kong/ai-marketplace/technical-writing"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/technical-writing/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/kong/ai-marketplace/technical-writing"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/technical-writing.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 | $0.00044 | $0.01954 |
| Opus 5.5 | $0.00018 | $0.00782 |
| Sonnet 5.5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
technical-writing 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical documentation writing
Goal
Write and edit developer-facing documentation that is easy to consume: plain, task-oriented, active-voice prose with scannable structure and clean punctuation. Own the words and their organization within a page.
Not Dev Portal specific, but it pairs with the portal skills: portal-page-design
for the components that hold the prose, portal-branding for appearance. Work in
page content files, locally or in a repo, and do not push destructive changes to a
live portal unless the user explicitly asks.
Clarify First
Ask two or three high-impact questions, each with a default to confirm:
- the reader and the task the page serves
- the source of truth for the technical details
- an existing page to match in tone and structure, if any
- the depth expected, from quickstart to full reference
Tool Selection
- Documenting Konnect resources: pull real details (control planes, services,
routes, specs) from real entities through the
kong-konnectMCP server instead of inventing values. If it is not connected, recommend installing it; otherwise ask the user for real values or mark them clearly as placeholders, not guesses. - Portal-page content: hand structure and components to
portal-page-designand keep this skill on the prose. - Follow Kong's documentation style guide for terminology and capitalization on Kong content; default to the Google and Microsoft developer style guides otherwise.
- Unsure of Kong terminology or how Kong documents a concept: check the server's Kong documentation knowledge base. If unavailable, rely on the style guides and flag anything you cannot confirm.
Workflow
- Name the reader and the task; lead with what the reader does.
- Choose the structure from that task and keep one use case on one page.
- Write in the house voice: second person, active voice, present tense, plain, front-loaded, scannable. Recommend choices with a reason.
- Make it self-contained: real values from MCP or the user, placeholders for reader-supplied values, one command per block, a verification step to close a how-to.
- Edit out the tells as a final pass.
- Match the density: cut a sentence that repeats the previous one; add one the reader would otherwise guess.
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 · 198 lines · 44 tokens per session scan A 8bab8b94fa26
technical-writing is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 44 tokens to every session and 1,954 once invoked, about $0.0002 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.
technical-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| technical-writingKong/ai-marketplace | Skill | 6 | 10d ago | MIT | A | 44 | Claude Code |
| ai-agentic-workflowsj4flmao/agent-skills | Skill | 38 | 3d ago | MIT | A | 151 | Claude Code, Codex |
| eclipse-license-checkTypeFox/agent-skills | Skill | 5 | 15d ago | MIT | A | 110 | Claude Code |
| idiomatic-goTypeFox/agent-skills | Skill | 5 | 15d ago | MIT | A | 137 | Claude Code |
| go-documentationTypeFox/agent-skills | Skill | 5 | 15d ago | MIT | A | 98 | Claude Code |
| publish-vscode-extensionTypeFox/agent-skills | Skill | 5 | 15d ago | MIT | A | 107 | Claude Code |
| plan-pmndisisnd/msg | Skill | 6 | 19d ago | MIT | A | 184 | Claude Code |