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/agents-mdgit 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/agents-md)<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>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 | $0.01104 | $0.01104 |
| Opus 5 | $0.00552 | $0.00552 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00110 | $0.00110 |
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.
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 testand confirm all tests pass. Do not commit with failing tests. - After adding a new tool: run
pnpm run linkto test the globalcontinues/contbinary locally. - Never run
pnpm run test:watch,e2e-conversions.test.ts,real-e2e-full.ts, orstress-test.tsin CI — these require live session files on the developer's machine.
Coding Standards
- ESM-only: all local imports must end in
.js, even for.tssource files (e.g.,import { foo } from './foo.js'). - No
any: Biome reportsnoExplicitAnyas a warning. Avoid it; document the reason if unavoidable. - Exit codes: set
process.exitCode = Nrather than callingprocess.exit(N). - Logging: use
loggerfromsrc/logger.tsfor all diagnostic output. Never use bareconsole.log/console.warn/console.errorin library code. TUI display goes through@clack/promptsorchalkvia the display layer. - Error types: throw typed errors from
src/errors.tson user-facing paths, not barenew Error(). - Tool activity: use
SummaryCollectorfromsrc/utils/tool-summarizer.tsin every parser. Do not buildToolUsageSummary[]arrays manually. - JSONL: use the shared streaming helpers in
src/utils/jsonl.ts, neverfs.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). Emptycatch {}blocks fail the linter; usecatch (err) { logger.debug(...) }instead.
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.
- 4d ago First seen · 53 lines · 1,104 tokens per session scan A 5ff76aa3a5a6
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.
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
Instructions for abhiunix/AgentHarbor, covering claude.md, commands, architecture, two tauri windows and adapter trait — the core abstraction.
AgentHarbor 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).