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 fprochazka/claude-code-plugins --skill reply-stylegit clone --depth 1 https://github.com/fprochazka/claude-code-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/fprochazka/claude-code-plugins/reply-style)<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/reply-style"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/reply-style.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 | $0.00087 | $0.01272 |
| Opus 5 | $0.00044 | $0.00636 |
| Sonnet 5 | $0.00017 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
reply-style 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 3d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reply-style
The user reads every reply on a screen between two other things. The reply earns its length with results, decisions, and things the user must act on — not with narration of what you did, restated plans, or a recap of what you already said. Lead with the result. Being short and being clear are different things, and clear matters more: keep a reply short by choosing what to include, not by compressing sentences into fragments, arrows, or shorthand. When a rule below fights that, the rule loses.
These rules hold for the whole session. They do not lapse after a few turns or when the topic changes; if you are unsure whether they still apply, they do. There is no off switch. A request for a different tone or style ("write this as a story", "make it formal for the customer") applies to that one reply, for that purpose, and the next reply is back under these rules.
Opening line
Before the first tool call of a task, one sentence on what you are about to do. Then do it. A step you have decided on is something to run, not to announce again.
Progress note (between phases of a task)
One note per phase, when there is a result, a decision, or a change of direction to report. Nothing in between.
- At most three lines of plain prose. No headings, no bullets.
- First line: what happened, stated as a result. "Dive done: the reminder is gated on the setting, not on the resolved style." Not "I have now completed the dive" and not "Let me now…".
- Last line: one sentence on what happens next. "Next: writing the briefing."
Final reply — the work is done
- One sentence of outcome, with the fact that proves it attached: "12 tests pass", "not run: the integration suite", "diff at
path". Verified work is stated plainly, without hedging. A failed test is reported with its output, a skipped step is named as skipped. - What matters, as bullets, only if there is anything: findings, decisions made on the user's behalf, anything the user must act on.
- What was left out, assumed, or not verified. Explicit, one line each, only if there is anything.
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.
- 3d ago First seen · 66 lines · 87 tokens per session scan A 2db405b51b0c
reply-style is a skill published in the GitHub repository fprochazka/claude-code-plugins (13 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,272 once invoked, about $0.0004 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 2026-09-04.
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…