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 bendrucker/claude --skill writinggit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/writing)<a href="https://agentmods.dev/skills/bendrucker/claude/writing"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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/bendrucker/claude/writing"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/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 | $0.00061 | $0.00707 |
| Opus 5.5 | $0.00024 | $0.00283 |
| Sonnet 5.5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
writing: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 10d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing
Write prose a person reads in a direct, conversational voice. The writing hooks lint saved files and outgoing messages against the Vale styles in styles/Writing/. The text is done when every alert the hook reports on it is fixed.
Voice
Every sentence teaches something new and holds only for this subject. Cut a sentence that restates the obvious or could move unchanged to another person, company, or product, or replace it with something true only of this subject.
- Prefer substance to filenames or implementation details.
- Prefer short sentences to compound constructions.
Rules
Structure
- Use no spaced em dash (
—). - Write each independent clause as its own sentence. A clause joined by an em dash, semicolon, hyphen, or any connector swapped in for one becomes a sentence break. Keep a semicolon only when the clauses can't stand alone.
- State the point directly in place of "not just X, but also Y" parallelism.
- Name a heading's topic in a couple of words: a noun phrase, without verbs or a
Topic: clauseform. Put the explanation in the body.
Word Choice
- Use "is" or "are" where "serves as" or "stands as" would go.
- Write "use X" or "prefer X over Y" in place of "reaching for X".
- Name what you're examining in place of "dig into" or "dive into".
- State a claim directly, or name the uncertainty, in place of hedging verbs ("looks like", "appears to", "seems to").
- Negate the verb with a contraction: "doesn't cost an extra query", "doesn't need a change". A positive term works when it names the state exactly ("a no-op", "unchanged"). Plain statements like "has no tests" and "there is no lock" stay.
- Say why something matters in place of gravity markers ("load-bearing", "the honest answer", "worth noting/flagging", "the full picture", "the cleanup story"): name what breaks without the dependency, or state the fact plainly.
PR and Review Prose
- Open a published comment on the substance, without a greeting or a name. Refer to people in third person by their username as written.
- Use active voice: "Adds X" in PR and review prose, "Add X" in commit subjects, "Added tests covering X" for tests.
- Describe what the tests cover in place of test counts, pass/fail tallies, or CI status.
- End a sentence on its content, without a trailing hedge adverb ("regardless.", "nonetheless.").
- State the positive directly in place of contrast by negation, whether across sentences ("It isn't X. It is Y.") or inline (
X, not Y).
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.
- 10d ago Changed · -2 lines 5859f2c4b87a
- 11d ago Changed 1b4153f38c5f
- 28d ago Changed fbc1b8574d9f
- 1mo ago Changed · +1 lines 2b35ee9d1366
- 2mo ago First seen · 50 lines · 61 tokens per session scan A fddfec3997e4
writing:writing is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
writing:writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing:writingbendrucker/claude | Skill | 18 | today | MIT | A | 61 | Claude Code |
| reviewSethGammon/Citadel | Skill | 928 | 4d ago | MIT | A | 17 | Claude Code |
| system-upgradealivecontext/alive | Skill | 132 | yesterday | MIT | A | 55 | Claude Code |
| wenlan-handoffwenlan-app/wenlan | Skill | 94 | today | Apache-2.0 | A | 43 | Claude Code, Codex |
| extract-resumesuxrobGM/jobpilot | Skill | 111 | today | MIT | A | 32 | Claude Code |
| pr-reviewnitinjain999/platform-skills | Skill | 71 | yesterday | Apache-2.0 | A | 81 | Claude Code |
| read-literaturefirecrawl/firecrawl-claude-plugin | Skill | 258 | 3d ago | MIT | A | 101 | Claude Code |