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 juliakrivchikova/AccordAgents-desktop-app --skill app-chat-replygit clone --depth 1 https://github.com/juliakrivchikova/AccordAgents-desktop-appWrote 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/juliakrivchikova/accordagents-desktop-app/app-chat-reply)<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/app-chat-reply"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/app-chat-reply/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/juliakrivchikova/accordagents-desktop-app/app-chat-reply"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/app-chat-reply.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 | $0.00041 | $0.00554 |
| Opus 5 | $0.00020 | $0.00277 |
| Sonnet 5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
app-chat-reply 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 11d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reply to a participant request
Use this skill when another participant triggered your turn through a participant request and your output is the reply they are waiting on.
A participant request is a structured ask from one participant to another. The requester is paused on your answer. In the normal path, answer directly in the active request thread; the app can attach an unambiguous reply to the request and resume the requester.
Do not use this skill when the user pinged you directly, when you are starting a new topic, or when no participant request is currently addressed to you.
Identify which request you are answering
Before you reply, decide exactly which request your answer belongs to.
- Look at the message that triggered your turn and the thread it was posted
in. The request you are answering is the pending participant request whose
targetis you and whosepromptmatches that triggering message in that thread. In normal operation there is exactly one. - If exactly one request is addressed to you and its prompt matches the triggering message, answer that request directly in the active thread.
- If two or more requests could plausibly match and the thread does not disambiguate, do not guess. Ask for clarification in one short normal chat message and end your turn.
- If zero requests are addressed to you, you were not triggered by a participant request. Answer as a normal chat message.
Reply
Write the answer directly in the current chat thread. If the requester asked for an exact format, output only that required content. If you cannot answer, state the blocker clearly in the reply.
Reading context
Use this order when deciding what to answer:
- The triggering message and its thread.
- Recent messages in the same thread, if any.
- App-provided request metadata in the current turn, if present.
Do not reread the full chat history unless the request cannot be understood from the triggering message, current thread, or request metadata.
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.
- 11d ago First seen · 63 lines · 41 tokens per session scan A 20a697dfefdc
app-chat-reply is a skill published in the GitHub repository juliakrivchikova/AccordAgents-desktop-app (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 554 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 2026-08-31.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…