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.
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/yigitkonur/cli-continues/parsersgit clone --depth 1 https://github.com/yigitkonur/cli-continuesWrote 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/yigitkonur/cli-continues/parsers)<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>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 | $0.00536 | $0.00536 |
| Opus 5 | $0.00268 | $0.00268 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00054 | $0.00054 |
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.
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.allSettledand 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 extractionextract<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.readFileSyncfor session files - Keep only the last ~10 messages in
recentMessages— do not accumulate the entire conversation
Tool Summarizer
- Always use
SummaryCollectorfromsrc/utils/tool-summarizer.ts— never buildToolUsageSummary[]arrays manually - Call
collector.add(category, summary, filePath?, isWrite?)for each tool invocation
Shared Helpers
- Import
cleanSummary,extractRepoFromCwd,homeDirfromsrc/utils/parser-helpers.ts - Do not duplicate these utilities in individual parser files
New Tool Checklist
Adding a new tool requires ALL five of:
- Parser file
src/parsers/<tool>.tsexporting both required functions - Registry entry in
src/parsers/registry.tswith allToolAdapterfields - Type update in
src/types/tool-names.ts— add toSessionSourceunion andTOOL_NAMESarray - Fixture factory in
src/__tests__/fixtures/index.ts - Conversion tests in
src/__tests__/unit-conversions.test.tsfor all N-1 paths in each direction
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 · 63 lines · 536 tokens per session scan A dcb809062b74
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.
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.
AgentHarbor CLAUDE.md
Claude Code instructions for abhiunix/AgentHarbor, covering claude.md, commands, architecture, two tauri windows and adapter trait — the core abstraction.
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.
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.
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.
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).