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/paleo/alignfirst/sharp-writingnpx skills add paleo/alignfirst --skill sharp-writinggit clone --depth 1 https://github.com/paleo/alignfirstWhat 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 | $0.00042 | $0.00837 |
| Opus 5 | $0.00021 | $0.00418 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
sharp-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 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sharp Writing
Write sharp text: every word counts. These rules cover all prose and Markdown.
Find the essence first
Before writing anything, find the essence of the idea. State the essence. State it well.
Principles
- Sharp, precise, concise. Straight to the point. The less, the better.
- Easy language. Keep sentences short and clear.
- Don't pad. No bloated orders, no filler.
- Respect the reader. No insistent or authoritarian tone; don't treat them like a child. Make what is important more obvious instead.
- Keep a formal register.
Weigh every word
Pick the word that says exactly what you mean. Prefer the common word; use an elaborate or technical one only when it is more precise.
Keep a formal register
Stay professional, without stiffness. Write complete sentences; don't clip the opening. No slang, no casual jargon, no emoticons.
Structure text like code
Good text is like good code:
- Avoid repeating or duplicating.
- Refactor text as you refactor code, so every idea is well-organized and clear.
One idea, one sentence. One concern, one paragraph. When a concern needs several paragraphs, give it a section title; split a complex idea into sub-ideas the same way. Never pack several ideas into one sentence, or several concerns into one paragraph. A sentence that chains clauses with colons and dashes is packing — split it.
Show the direct path, not your detours. Writing is like climbing an uncharted mountain: you wander and backtrack to find the way, then from the summit you see the straight route. Write that route. Readers want the direct path, not the search that found it.
Prefer positive phrasing
Say what is, not what is not. A negation forces the reader to invert; a double negation forces two inversions.
Cut the negated echo
A common reflex: affirm, then restate the same idea negated — "X is A, not B", where B is merely the absence of A. Cut the negated half.
Stop at the last fact
End when the information ends. Don't close with a sentence that restates the point, draws a moral, or justifies what you just wrote. Before keeping a final sentence, check it carries a new fact or instruction. If it only emphasizes, concludes, or reassures, cut it.
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 · 91 lines · 42 tokens per session scan A b792052f9b21
sharp-writing is a skill published in the GitHub repository paleo/alignfirst (85 stars, last pushed 3d ago), licensed CC0-1.0. It adds 42 tokens to every session and 837 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 skills, from other repositories
vibe-to-agentic-framework
The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
presentation-structure
Knowledge about the presentation slide format, weight system, navigation, and section structure.
presentation-styling
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation.
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
time-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.