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 instructions/sharptrick/parley/claude-mdgit 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/instructions/sharptrick/parley/claude-md)<a href="https://agentmods.dev/instructions/sharptrick/parley/claude-md"><img src="https://agentmods.dev/badge/instructions/sharptrick/parley/claude-md.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 | $0.01879 | $0.01879 |
| Opus 5 | $0.00940 | $0.00940 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
parley CLAUDE.md 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Parley build instructions
You are building Parley, a transport-agnostic seam MCP that carries messages, shared context, and task hand-off between humans, online chat bots, and coding agents over a pluggable messaging backend.
Read DESIGN.md in full before writing any code. It is the source of truth. This file is
the operating manual: how to work, in what order, and the rules that keep an autonomous run
on-rails. TASKS.md is the ordered checklist — work it top to bottom, checking items off as
you complete and verify them.
Prime directives
-
The seam is the product. Everything hard lives behind one small interface (
connect / disconnect / subscribe / post / fetchRecent / resolveIdentity).bridge-coremust never import from a backend plugin. Dependencies point one way: plugins depend on core, never the reverse. If you ever feel the urge to special-case a backend inside core, stop — the seam is wrong; fix the seam, not with a branch in core. -
Success criterion for every backend after the first: adding it touches only the new plugin package, never
bridge-core. If core has to change to fit a backend, that is a design smell to surface, not silently absorb. -
Build in the order in
TASKS.md. Do not skip ahead. v0.1 (SQLite) is the seam-proving gate; nothing else starts until it works end to end against the fakechat loopback. -
One channel gate, verify first (see below). Before implementing the live-push half, verify the current channel contract from the docs. Do not build the push path from memory or from
DESIGN.md's summary of it.
The channel-docs verification gate (MANDATORY before any push code)
DESIGN.md describes how Claude Code Channels work, but the exact <channel> event
schema, the claude/channel capability declaration, and the reply/tool-registration details
must come from the live docs, not from this package's summary.
Before writing the v0.1 push half (TASKS step P-1):
- Fetch and read
https://code.claude.com/docs/en/channelsandhttps://code.claude.com/docs/en/channels-reference(or current equivalents). - Confirm: how a server declares
claude/channel; the exact shape of the<channel>event pushed into the session; how reply/react/edit-style tools are registered; how--channelsloads a custom (development) channel; and the current auth requirement (claude.ai subscription, not API key). - If the docs and
DESIGN.mddisagree, the docs win — note the discrepancy in your progress notes and follow the docs. - Develop and test the push path against the fakechat loopback
(
--channels plugin:fakechat@claude-plugins-official, behind--dangerously-load-development-channelsduring the research preview) before wiring any real backend'ssubscribe.
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 · 138 lines · 1,879 tokens per session scan A d91d82ed391f
parley CLAUDE.md is an instructions file published in the GitHub repository sharpTrick/parley (0 stars, last pushed 27d ago), licensed MIT. It adds 1,879 tokens to every session, about $0.0094 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.