cli-continues AGENTS.md

cli-continues AGENTS.md is an instructions file for Codex, OpenCode from yigitkonur/cli-continues. It costs 1,104 tokens per session, scanned A, original, MIT.

Project instructions for cli-continues, a command-line tool that continues AI sessions across tools. They describe its workflow, coding rules, tests, and how to add parsers and tools.

In plain words
What is it for?
Use them when changing parsers, fixtures, or tools in cli-continues, especially before running checks, tests, or its local linking command.
Why use it?
They give contributors concrete checks and conventions that reduce broken builds, inconsistent imports, and unsafe test or logging practices.

Instructions file for CodexOpenCode

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/yigitkonur/cli-continues/agents-md
Clone the repo
git clone --depth 1 https://github.com/yigitkonur/cli-continues

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for cli-continues AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yigitkonur/cli-continues/agents-md.svg)](https://agentmods.dev/instructions/yigitkonur/cli-continues/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yigitkonur/cli-continues/agents-md"><img src="https://agentmods.dev/badge/instructions/yigitkonur/cli-continues/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,104 This file is loaded in full into every session.
When invoked 1,104 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 $0.01104 $0.01104
Opus 5 $0.00552 $0.00552
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00110 $0.00110

Measured 4d ago against content hash 5ff76aa3a5a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-continues AGENTS.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 4d 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.

AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Agent behavior instructions for continues — the cross-tool AI session handoff CLI. Read CLAUDE.md for architecture, types, and the step-by-step guide for adding a new parser. This file covers workflow, coding standards, and anti-patterns.

Workflow

  • Before any commit: run pnpm run check (pnpm lint && pnpm build). Fix all Biome errors; warnings are advisory.
  • After changing a parser or fixture: run pnpm test and confirm all tests pass. Do not commit with failing tests.
  • After adding a new tool: run pnpm run link to test the global continues / cont binary locally.
  • Never run pnpm run test:watch, e2e-conversions.test.ts, real-e2e-full.ts, or stress-test.ts in CI — these require live session files on the developer's machine.

Coding Standards

  • ESM-only: all local imports must end in .js, even for .ts source files (e.g., import { foo } from './foo.js').
  • No any: Biome reports noExplicitAny as a warning. Avoid it; document the reason if unavoidable.
  • Exit codes: set process.exitCode = N rather than calling process.exit(N).
  • Logging: use logger from src/logger.ts for all diagnostic output. Never use bare console.log/console.warn/console.error in library code. TUI display goes through @clack/prompts or chalk via the display layer.
  • Error types: throw typed errors from src/errors.ts on user-facing paths, not bare new Error().
  • Tool activity: use SummaryCollector from src/utils/tool-summarizer.ts in every parser. Do not build ToolUsageSummary[] arrays manually.
  • JSONL: use the shared streaming helpers in src/utils/jsonl.ts, never fs.readFileSync + split('\n').
  • SQLite (OpenCode, Crush parsers): use built-in node:sqlite — do not add third-party SQLite dependencies.
  • Biome rules in force: noEmptyBlockStatements (error), noUnusedImports (error), useConst (error). Empty catch {} blocks fail the linter; use catch (err) { logger.debug(...) } instead.

Read the full file on GitHub · 53 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. 4d ago First seen · 53 lines · 1,104 tokens per session scan A 5ff76aa3a5a6

Subscribe to this mod's changes

cli-continues AGENTS.md is an instructions file published in the GitHub repository yigitkonur/cli-continues (1,479 stars, last pushed 3mo ago), licensed MIT. It adds 1,104 tokens to every session, about $0.0055 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 2026-08-30.

Related

Other instructions, from other repositories