cli-continues parsers.instructions.md

cli-continues parsers.instructions.md is an instructions file for GitHub Copilot from yigitkonur/cli-continues. It costs 536 tokens per session, scanned A, original, MIT.

A set of rules for reviewing parsers, which read session data and turn it into a common format. It covers crash safety, required functions, JSONL files, and registration.

In plain words
What is it for?
Use it when implementing or reviewing parsers, handling bad JSONL lines, extracting tool activity, and registering parser adapters.
Why use it?
It prevents malformed input or parser errors from silently removing sessions from the index.

Instructions file for GitHub Copilot

About the project

continues is a command-line tool for moving an AI coding session from one coding agent to another while preserving conversation history, file changes, and working state. Developers use it when they need to continue work in a different tool, and the catalogue entries provide instructions for transferring sessions across supported agents.

yigitkonur/cli-continues · 1,483 stars · on GitHub

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

Made for: GitHub Copilot.

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 parsers.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yigitkonur/cli-continues/parsers.svg)](https://agentmods.dev/instructions/yigitkonur/cli-continues/parsers)
Your own site
<a href="https://agentmods.dev/instructions/yigitkonur/cli-continues/parsers"><img src="https://agentmods.dev/badge/instructions/yigitkonur/cli-continues/parsers.svg" alt="Measured on agentmods" height="20"></a>
Per session 536 This file is loaded in full into every session.
When invoked 536 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 $0.00536 $0.00536
Opus 5 $0.00268 $0.00268
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00054 $0.00054

Measured 5d ago against content hash dcb809062b74, 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 parsers.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 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.

.github/instructions/parsers.instructions.md · 63 lines

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.

Parser Review Guidelines

Crash Safety (Critical)

  • Parsers MUST NOT throw to the caller — each runs inside Promise.allSettled and an uncaught error silently drops that tool's sessions from the index
  • Wrap JSON.parse calls and file-read loops in try-catch with an empty catch block to silently skip malformed data
// Good — CLI continues if one line is malformed
for (const line of lines) {
  try {
    const data = JSON.parse(line);
    // process...
  } catch {
    // Skip malformed line silently
  }
}

// Bad — one bad line crashes the entire parser
for (const line of lines) {
  const data = JSON.parse(line);
}

Required Exports

Each parser file must export exactly two functions:

  • parse<Tool>Sessions(): Promise<UnifiedSession[]> — file discovery and metadata extraction
  • extract<Tool>Context(session: UnifiedSession, config?: VerbosityConfig): Promise<SessionContext> — full conversation and tool activity extraction

Both must be registered in src/parsers/registry.ts with all ToolAdapter fields populated.

JSONL Streaming

  • Stream JSONL with helpers from src/utils/jsonl.ts (readJsonlFile, scanJsonlHead) when applicable
  • Never use fs.readFileSync for session files
  • Keep only the last ~10 messages in recentMessages — do not accumulate the entire conversation

Tool Summarizer

  • Always use SummaryCollector from src/utils/tool-summarizer.ts — never build ToolUsageSummary[] arrays manually
  • Call collector.add(category, summary, filePath?, isWrite?) for each tool invocation

Shared Helpers

  • Import cleanSummary, extractRepoFromCwd, homeDir from src/utils/parser-helpers.ts
  • Do not duplicate these utilities in individual parser files

New Tool Checklist

Adding a new tool requires ALL five of:

  1. Parser file src/parsers/<tool>.ts exporting both required functions
  2. Registry entry in src/parsers/registry.ts with all ToolAdapter fields
  3. Type update in src/types/tool-names.ts — add to SessionSource union and TOOL_NAMES array
  4. Fixture factory in src/__tests__/fixtures/index.ts
  5. Conversion tests in src/__tests__/unit-conversions.test.ts for all N-1 paths in each direction

Read the full file on GitHub · 63 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. 5d ago First seen · 63 lines · 536 tokens per session scan A dcb809062b74

Subscribe to this mod's changes

cli-continues parsers.instructions.md is an instructions file published in the GitHub repository yigitkonur/cli-continues (1,483 stars, last pushed 4mo ago), licensed MIT. It adds 536 tokens to every session, about $0.0027 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

skills CLAUDE.md

Claude Code instructions for lovstudio/skills, covering claude.md, what this is, repo layout, how users install and skills.yaml schema.

lovstudio/skills · 1,821 tokens

AgentHarbor CLAUDE.md

Claude Code instructions for abhiunix/AgentHarbor, covering claude.md, commands, architecture, two tauri windows and adapter trait — the core abstraction.

abhiunix/AgentHarbor · 2,538 tokens

AgentHarbor AGENTS.md

AGENTS.md instructions for abhiunix/AgentHarbor, a project described as: 🚢 One native app for all your AI coding agents - live rate limits, session usage, deep analysis of your & monthly spend for Claude Code, Cursor, Codex, Gemini etc plus one-click MCP/rules/skills/sub-agent deploy.

abhiunix/AgentHarbor · 206 tokens

agent-hook-schemas CLAUDE.md

Claude Code instructions for mherod/agent-hook-schemas, covering claude.md, build & test commands, npm publish, architecture and key patterns.

mherod/agent-hook-schemas · 3,428 tokens

Dragon-Brain CLAUDE.md

Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.

iikarus/Dragon-Brain · 6,132 tokens

myPKA CLAUDE.md

Claude Code instructions for myICOR/myPKA, covering claude.md, first run check (read this before doing anything else), identity (mandatory — applies every session), source of truth and specialist dispatch (claude code specific).

myICOR/myPKA · 1,246 tokens