lazychat copilot-instructions.md

Repository instructions for Lazychat, a Bun and TypeScript project that uses a shared Markdown file as an asynchronous discussion thread between a person and an AI agent. They define its runtime, release method, file protocol, and coding rules.

In plain words
What is it for?
Use them when developing, running, packaging, or documenting Lazychat.
Why use it?
They prevent changes that would break the discussion protocol, use the wrong runtime, or assume the project is distributed through npm.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/fgrehm/lazychat/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/fgrehm/lazychat

Made for: GitHub Copilot.

Per session 999 This file is loaded in full into every session.
When invoked 999 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00999 $0.00999
Opus 5 $0.00500 $0.00500
Sonnet 5 $0.00200 $0.00200
Haiku 4.5 $0.00100 $0.00100

Measured 2d ago against content hash b02c9508766b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lazychat copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository instructions for Copilot

lazychat is a file-based async discussion protocol: a shared markdown file in the working tree acts like an email thread between a human and an AI agent. See README.md and SKILL.md for the protocol itself.

Runtime and distribution

  • This is a Bun project, not a Node.js project. TypeScript sources are the entry points (src/cli/index.ts, src/index.ts) and run directly via the #!/usr/bin/env bun shebang. engines.bun in package.json declares the runtime requirement.
  • Distribution is via compiled binaries published to GitHub Releases (bun build --compile), not npm. No npm publish is planned in v0.0.x. Do not suggest publishing .js artifacts, building a JS shim, or changing main/exports/bin away from .ts paths. The .ts entries are intentional and will stay until npm publishing is explicitly back on the table.
  • Assets bundled into the binary (e.g. SKILL-CLI.md) are embedded with Bun text imports: import X from "./file.md" with { type: "text" }.

Protocol invariants

  • Threads are append-only. Never edit or reorder prior turns.
  • The protocol is stop-and-wait: the agent writes, stops, and waits for the human. Concurrent writers are out of scope; locking or optimistic-concurrency schemes are not required unless the scope explicitly changes.
  • Turn headers are written as ## Round N (role) - @model-id with a plain hyphen. The parser also accepts U+2013 (en-dash) and U+2014 (em-dash) so older threads and hand-typed turns parse cleanly. This forgiveness is intentional.
  • A thread with status: converged is read-only.

Code conventions

  • Prefer editing existing files to adding new ones. Do not introduce scaffolding, feature flags, or backwards-compat shims for hypothetical future requirements.
  • Default to no comments. Add a comment only when the why is non-obvious (hidden constraint, subtle invariant, documented workaround). Do not restate what well-named code already conveys.
  • Use ASCII quotes (" and ') in code and strings, not Unicode typographic quotes. Formatters restore Unicode on commit and cause staged diffs to flip back.
  • In prose (comments, docs, commit messages), use commas, periods, or parentheses for mid-sentence breaks. Not em-dashes or double-dashes.
  • File writes must be atomic: use the atomicWrite helper (temp file in the same directory + rename) for updates, or writeFile({ flag: "wx" }) for exclusive create. Do not propose plain overwriting writes.
  • Skip marketing fluff in docs and reviews ("comprehensive", "robust", "seamless", "cutting-edge"). Be direct.
  • When a let is assigned across if/else branches, give it an explicit type annotation. TypeScript narrows it correctly under strict, but reviewers may flag the bare declaration as implicit any.

Read the full file on GitHub · 43 lines

Changes

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.

  1. 2d ago First seen · 43 lines · 999 tokens per session scan A b02c9508766b

Subscribe to this mod's changes

lazychat copilot-instructions.md is an instructions file published in the GitHub repository fgrehm/lazychat (5 stars, last pushed 4mo ago), licensed MIT. It adds 999 tokens to every session, about $0.0050 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens