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 | $0.00022 | $0.00977 |
| Sonnet 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 12d 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.
- 12d 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 (5 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 1,954 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Owns the requirements interview — fleshes out thin ideas, proactively…
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…
plan-pm
Principal PM skill — the autonomous PRD writer. Consumes a graded, fleshed-out row from the INTAKE.md backlog (idea, goal, type, grade) and drafts the full PRD solo — feature/acceptance table, edge cases, error handling — saved to features/planned/prd-[n]-[feature-slug]/. The requirements interview lives in /intake…