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 sharpTrick/parley --skill chat-handoffgit clone --depth 1 https://github.com/sharpTrick/parleyWrote 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/sharptrick/parley/chat-handoff)<a href="https://agentmods.dev/skills/sharptrick/parley/chat-handoff"><img src="https://agentmods.dev/badge/skills/sharptrick/parley/chat-handoff.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 | $0.00089 | $0.01099 |
| Opus 5 | $0.00044 | $0.00549 |
| Sonnet 5 | $0.00018 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
chat-handoff 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat handoff (Parley)
Chat-side conventions for Parley — the transport-agnostic seam connecting a Claude chat
session, a Claude Code session, and humans over a shared messaging backend. The chat instance is a
first-class consumer of the same agnostic bridge MCP, using only the standard-MCP subset:
parley_post and parley_fetch_recent. It does not use live subscribe (chat cannot receive
pushes). This skill is documentation of usage, not a second integration — do not install a
backend-specific (Matrix/XMPP) MCP in chat; that would bypass the normalized message shape
(handle, cursor, mentions) catch-up relies on.
When to use
- The user wants to hand a task to a coding agent ("take this to Claude Code", "have the agent build it").
- The user wants to share the context built up in this chat with a Code session.
- The user wants to see what a Code session — or a human — has posted on a topic.
Tools
parley_fetch_recent { topic, since?, limit?, block_ms? }— read recent messages on a topic. Returns{ messages, nextCursor }. Call it first to catch up; pass the previousnextCursorassinceto page forward. Ordering/dedup usecursor, never timestamps. Passblock_msto long-poll — see "Waiting efficiently" below.parley_post { topic, content, in_reply_to? }— publish a message (a handoff or a note) so the Code session and humans see it durably.
How to hand off
- Pick the topic. Use the topic the user names, or the conventional context topic for the
work (e.g.
ctx-payments). One topic = one thread of work. - Catch up first. Call
parley_fetch_recenton the topic so your handoff doesn't repeat what's already there. - Post a self-contained handoff. The Code agent may have none of this chat's context. Include:
- Goal — what to accomplish.
- Context — key decisions/constraints from this chat (paths, links, prior art).
- Acceptance — how to know it's done.
- @mention the target handle (e.g.
@ctx-payments) if mention-filtering is enabled.
- Confirm to the user that the handoff was posted, and to which topic.
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.
- 7d ago First seen · 87 lines · 89 tokens per session scan A d234e5f97e2a
chat-handoff is a skill published in the GitHub repository sharpTrick/parley (0 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,099 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 2026-08-31.
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…