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 jonZlotnik/how-to-agent --skill prefer-active-voicegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/prefer-active-voice)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/prefer-active-voice"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prefer-active-voice/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/jonzlotnik/how-to-agent/prefer-active-voice"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/prefer-active-voice.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 | $0.00050 | $0.00530 |
| Opus 5 | $0.00025 | $0.00265 |
| Sonnet 5 | $0.00010 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
prefer-active-voice 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prefer Active Voice
Passive voice hides the actor, and in technical prose the actor is usually the information the reader needs. "The file is deleted" does not say who deletes it or when. "The daemon deletes the file after upload" does. Default to active; use passive only as a deliberate choice.
When to use
- A sentence uses a form of "be" plus a past participle: "is handled", "was created", "are validated"
- A reader could ask "by whom?" or "by what?" and the text does not answer
- An error message or doc leaves the responsible component unnamed
- A commit message says what "was changed" instead of what the change does
Protocol
- Find the passives. Search the text for "is/are/was/were/been/being" followed by a past participle.
- Name the actor you can verify. "The config is read at startup" → "The server reads the config at startup" — only if the code or observed behavior confirms the server does it. If you cannot verify the actor, keep the passive rather than guess: a wrong actor is a fabricated fact, and worse than a missing one.
- Keep passive only on purpose. When the actor is truly unknown or irrelevant ("the packet was corrupted in transit"), passive is correct. Make it a decision, not a default.
- Recheck the revision. Scan the result for remaining passives. Fix each one or record why it stays.
Example
Before: The cache is invalidated when the config is changed.
After: Saving the config invalidates the cache.
Red flags (rationalizations to reject)
- "Passive sounds more objective." — It sounds evasive. Objectivity comes from accuracy, not hidden actors.
- "We don't want to assign blame." — Name the component, not a person: "the migration dropped the index".
- "Everyone writes docs this way." — Common is not clear. The reader still has to guess the actor.
Composes with
- [[omit-needless-words]] — active rewrites are usually shorter.
- [[consistent-terminology]] — naming the actor forces you to pick its one canonical name.
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.
- 11d ago First seen · 41 lines · 50 tokens per session scan A 2c8e222d1e20
prefer-active-voice is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 530 once invoked, about $0.0003 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
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…