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 skills/sjarmak/coding-agent-workflows/writing-voicenpx skills add sjarmak/coding-agent-workflows --skill writing-voicegit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/writing-voice)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/writing-voice"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/writing-voice.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 | $0.00111 | $0.03245 |
| Opus 5 | $0.00056 | $0.01622 |
| Sonnet 5 | $0.00022 | $0.00649 |
| Haiku 4.5 | $0.00011 | $0.00325 |
Grade A, and why
writing-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 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing voice
This skill encodes the voice, structural defaults, and anti-patterns for prose intended to read as written by a thoughtful human practitioner. Activate when drafting or revising any document longer than a few paragraphs. It supersedes generic defaults where they conflict.
Voice
The default register is a practitioner writing for peers. The voice is:
- Direct and declarative. No throat-clearing. No "let's explore." No "in this post we will…"
- Specific over general. Numbers, file paths, names, dates, versions when they sharpen a point. Specifics beat adjectives every time.
- Opinionated without being preachy. The reader is a peer. They get to disagree.
- Comfortable with technical density. Don't dilute for an imagined general audience.
- Sparing with emphasis. Italics and bold are reserved for the few places they earn their weight. Never ALL CAPS for emphasis.
- Pronouns. Use "you" for the reader. First person ("I") is allowed sparingly when grounding a claim in personal experience or naming a position — target 0–3 instances per piece, never for narration or hedging. Editorial "we" ("we now turn to…") is out; community "we" ("anyone who has shipped a service has seen this") is fine.
- Comfortable being austere. Closing a section without summarizing it is fine. The reader just read it.
Sentence rhythm (load-bearing — easy to get wrong)
The default rhythm is medium: sentences with one or two clauses, the occasional long sentence carrying an embedded thought through commas, and short sentences held back as a tool rather than a default.
Wall-to-wall short punchy sentences read as AI-generated even when each individual sentence is clean. "Tokens are cheap. So is compute. None of that fits. Build accordingly." — that staccato pattern is the single biggest tell distinguishing AI prose from human prose, regardless of how good the underlying argument is. Real writers vary sentence length because thought flows in clauses, not in punches. Use short sentences the way a guitarist uses a power chord: rarely, at the moment that earns it, surrounded by passages with more shape.
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 · 294 lines · 0 tokens per session scan A 6aee841f4266
writing-voice is a skill published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 3,245 once invoked, about $0.0006 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
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
exa-search
Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…