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 fprochazka/claude-code-plugins --skill technical-writinggit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWrote 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/fprochazka/claude-code-plugins/technical-writing)<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/technical-writing"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/technical-writing.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.01847 |
| Opus 5 | $0.00049 | $0.00924 |
| Sonnet 5 | $0.00020 | $0.00369 |
| Haiku 4.5 | $0.00010 | $0.00185 |
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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
technical-writing
The reader can read the code. Text earns its place by saying what the code cannot: why it is this way, what will surprise the reader, what it connects to. Everything else is a restatement that goes stale the day the code changes.
What to write down
- Why, not what. Decisions, trade-offs, constraints: "orders are versioned by validity period because the legal export must reproduce any past state". Not "the entity has validFrom and validTo".
- Gotchas. Surprising behavior, implicit contracts, the thing that is easy to get wrong: "this repository queries the legacy schema directly; there is no entity to look for".
- Business meaning. What a value means to the domain and why anyone cares: "a sell-off promotion means purchasing over-ordered; it should feed the next forecast".
- Non-obvious relationships. How parts feed each other, especially when the data flow is not visible from one file: "requirements are computed from forecast plus reservations, never stored".
- Legacy reasons. Why something looks odd today: "the
sitestable holds warehouses; the name predates the warehouse model". This is the one kind of history worth keeping.
What not to write down
- Lists of classes, methods, files, or endpoints. They go stale at once and the reader can search.
- Column descriptions, config values, environment settings. They live in the schema, the annotations, and the config files.
- The pattern, at the place where it is used. A project convention is documented once, in the central place for conventions; a use of it gets at most a pointer ("follows the repository convention, see docs/conventions"). A deviation from the pattern is documented where it happens, with its reason.
- Anything the code says in thirty seconds of reading.
- The change. "Previously X, now Y", "renamed from", "no longer", "this commit adds" belong to git, not to docs or comments. Describe the current state only.
- Ticket references in code comments, schema comments, migrations, or descriptions. They belong in the commit and the MR.
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.
- 4d ago First seen · 74 lines · 99 tokens per session scan A 31f6e1ce766e
technical-writing is a skill published in the GitHub repository fprochazka/claude-code-plugins (14 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,847 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…