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/triumph-tech/rock-claude-plugins/write-like-menpx skills add Triumph-Tech/rock-claude-plugins --skill write-like-megit clone --depth 1 https://github.com/Triumph-Tech/rock-claude-pluginsWrote 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/triumph-tech/rock-claude-plugins/write-like-me)<a href="https://agentmods.dev/skills/triumph-tech/rock-claude-plugins/write-like-me"><img src="https://agentmods.dev/badge/skills/triumph-tech/rock-claude-plugins/write-like-me.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 | $0.00179 | $0.01996 |
| Opus 5 | $0.00089 | $0.00998 |
| Sonnet 5 | $0.00036 | $0.00399 |
| Haiku 4.5 | $0.00018 | $0.00200 |
Grade A, and why
write-like-me 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 5d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write In My Voice
This skill drafts communications that sound like the author wrote them, then polishes the result against high quality standards — without undoing what makes the author's writing distinctive.
The key difference between this and a generic writing assistant: the polish pass is voice-aware. Writing Coach rules that would normally cut a word or pattern get checked against the author's style guide first. If the style guide marks something as intentional, it stays.
Phase 1: Find and Read the Style Guide
Before asking the author anything, find their style guide.
Look for it at:
[workspace root]/context/style-guide.md
To find the workspace root, check for a CLAUDE.md in the current working directory — it typically identifies the workspace folder path.
Read the entire style guide. Don't skim. Then build two internal reference lists before proceeding:
Voice-protected patterns — things the style guide explicitly marks as intentional that Writing Coach rules might otherwise remove. Look for:
- Characteristic softener words ("just," "actually," "quick," etc.)
- Recurring phrases ("I'd love to," "on your end," "happy to," etc.)
- Deliberate structural choices (how bad news is framed, how conflict is routed)
- Sign-off and greeting patterns
- Sentence rhythm patterns (fragments, specific opener structures)
- Pronoun patterns ("we" vs. "I" distinctions)
Structural rules — the author's preferences for length, paragraph density, punctuation choices, and formatting. Exception: em-dashes are never used regardless of what the style guide shows.
If the style guide is missing or the path can't be resolved, tell the author and suggest they run the build-my-style-guide skill first. Do not attempt to draft without it.
Phase 2: Gather Framing
Ask these four questions in a single AskUserQuestion call. If the author has already answered some of them in their request, pre-fill those and only ask for the gaps.
- What type of piece is this? (email, Slack message, all-staff announcement, partner update, blog post, social post, memo, etc.)
- Who is the audience? (specific person, team, clients/partners, all staff, the public, etc.)
- What are your main points? (let them brain-dump in any order — substance over structure at this stage)
- How do you want them to respond or feel? (the desired emotional or behavioral outcome — calm, energized, aligned, willing to act, informed, etc. — but also strategic business outcomes: book a call, open a door to a future conversation, agree to a next step, shift their perception, etc.)
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.
- 5d ago First seen · 126 lines · 179 tokens per session scan A 840e72823d97
write-like-me is a skill published in the GitHub repository Triumph-Tech/rock-claude-plugins (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 179 tokens to every session and 1,996 once invoked, about $0.0009 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…
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…
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…