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 leifericf/agentic-sdk --skill write-prosegit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/leifericf/agentic-sdk/write-prose)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/write-prose"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/write-prose.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 | $0.00065 | $0.02364 |
| Opus 5 | $0.00032 | $0.01182 |
| Sonnet 5 | $0.00013 | $0.00473 |
| Haiku 4.5 | $0.00006 | $0.00236 |
Grade A, and why
write-prose 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-prose
Invoke this skill for any English you produce in this project: commits, comments, docstrings, ADRs, design docs, skill bodies, changelog, error messages, project guides. If you are about to write a sentence of prose, invoke this first.
Read this before writing:
skills/shared/references/style-foundations.md, the canonical craft
reference. It distills Strunk and White's Elements of Style and
Zinsser's On Writing Well into the eight load-bearing rules, and
catalogs the AI tells the project bans.
Also read for project-specific surfaces:
skills/shared/references/prose-style.md, the project's surface
conventions (commit format, ADR format, code-comment idioms, the
no-process-ID rule).
The stance: terse, humanized, no tells
Write like a person who respects the reader's time. Not like a machine hedging its output. The default failure mode for AI prose is over-production: too many words, decorative em dashes, sympathetic throat-clearing, false-affinity adjectives (powerful, robust, seamless). Reject that default at every sentence.
The four non-negotiables:
- Terse. Omit needless words. The first draft is too long; the second is shorter. If a sentence can be cut and lose no meaning, cut it.
- Humanized. Write like a careful person, not a helpful machine. No apologetic throat-clearing, no false brightness. No filler.
- No em dashes. Never the em dash character. Restructure: a comma, a colon, a period, or a rewrite. Reaching for the em dash means the sentence is doing too much.
- No AI tells. No arrow in prose, no hand-written or hand-rolled,
no false-affinity adjectives, no hollow hedging, no rhetorical-question
transitions, no in order to (just to), no utilize or leverage (just
use), no There is openers, no trendy intensifiers (really, very,
super). The full catalog is in
style-foundations.md.
The voice (every surface)
- Plain, direct, technical. No metaphors, no cleverness in names or headings. A reader six months from now gets the plain meaning on first read.
- Active voice; present tense for current behavior, past tense for history.
- State constraints and effects, not narrative.
- No marketing adjectives. If a property matters, state the measurement or the mechanism.
- Factual, neutral, accurate. State what the thing is and what it does, not how it feels or how exciting it is. No editorial comparisons ("improves on X"); state the factual difference and let the reader judge.
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 · 235 lines · 65 tokens per session scan A a8e3e46cfc37
write-prose is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 2,364 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 2026-09-03.
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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…