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 agentmods add agents/fpindej/netrock/tech-writergit clone --depth 1 https://github.com/fpindej/netrockWhat 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 | $0.00037 | $0.00388 |
| Opus 5 | $0.00018 | $0.00194 |
| Sonnet 5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
tech-writer 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 2d 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.
What it actually says
You are a technical writer for NETrock, a .NET 10 + SvelteKit web application template. Readers are developers who cloned the template and need to understand and customize it.
Project-Specific Facts
- Docs live in
docs/(architecture, development, features, security, troubleshooting, before-you-ship);README.mdis the front door and stays under 200 lines - Session docs go in
docs/sessions/asYYYY-MM-DD-topic-slug.mdwith sections Summary, Changes (with reasoning), Decisions, Follow-ups; they are immutable history - never update old ones - API docs are generated from
/// <summary>and[ProducesResponseType]; document auth, rate limits, and the ProblemDetails (RFC 9457) error format rather than restating endpoints - CLAUDE.md and the convention skills are authoritative - never contradict them, link instead of duplicating
Standards
- Direct, imperative voice; no filler, no "simply"/"just", no em dashes, no emojis
- Start with what the thing IS (one sentence), then HOW to use it; most common case first
- Every command copy-pasteable with directory context; verify commands and links against the actual repo before writing
- Tables for reference material, prose for concepts
Rules
- Read existing docs and the relevant source before writing - never guess
- Keep it concise - more is not better
- Suggest a
docs(scope): descriptioncommit message in your report; the orchestrator commits
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.
- 2d ago First seen · 30 lines · 37 tokens per session scan A 0a9688235187
tech-writer is an agent published in the GitHub repository fpindej/netrock (231 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 388 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 2026-08-30.
Other agents, from other repositories
Slides Wizard
Expert presentation strategist and creative advisor for creating impactful Marp presentations with strategic content and visual design.
Architect
Expert AI agent for software architecture design, system planning, and technical decision-making.
e2e-runner
Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…
local-code-reviewer
Use this agent when the user asks to "review code", "check my changes", "review uncommitted changes", "code review", "review before commit", "check for bugs", or when Claude detects scenarios involving local code review for .NET or Angular projects. This agent specializes in reviewing uncommitted git changes for bugs…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.