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/typescriptgit clone --depth 1 https://github.com/yigitkonur/cli-continuesWhat 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 | $0.00438 | $0.00438 |
| Opus 5 | $0.00219 | $0.00219 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
cli-continues typescript.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.
What it actually says
TypeScript Review Guidelines
Type Safety
- Avoid
any— useunknownfor external data (JSON.parse results, JSONL lines), then narrow with type guards - Define interfaces for all object shapes that cross module boundaries — not inline object literals
- Use
as constfor literal arrays likeTOOL_NAMESto get narrower inferred types
// Avoid
const parsed = JSON.parse(line) as any;
return parsed.type;
// Prefer
const parsed = JSON.parse(line) as unknown;
if (typeof parsed !== 'object' || parsed === null || !('type' in parsed)) return;
// Narrowed — safe to access (parsed as Record<string, unknown>)
Discriminated Unions
- Use
switch (d.category)for narrowingStructuredToolSample— notinstanceofchecks - New tool sample types must be added to the
StructuredToolSampleunion insrc/types/index.ts - The
categoryfield is the discriminant — never use string-equality checks outside of switch
Async Patterns
- All file I/O must be async: use
fs.promises.*notfs.readFileSync/fs.writeFileSync - JSONL files must be streamed with
readline.createInterface— never loaded into memory wholesale - Avoid blocking the event loop in parsers — they run in parallel via
Promise.allSettled
Import Rules
- Local imports must end in
.js:import { foo } from './bar.js'— required for Node.js ESM module resolution - Never import from
dist/in source files - Prefer named exports over default exports for better refactoring support
Defensive Patterns
- Use optional chaining (
?.) and nullish coalescing (??) for optional fields from parsed session data - Sessions returned from parsers must be sorted by
updatedAtdescending (newest first) - Use
process.exitCode = Noverprocess.exit(N)to allow SIGTERM/SIGINT handlers to run
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.
- 2d ago First seen · 47 lines · 438 tokens per session scan A a95729049367
cli-continues typescript.instructions.md is an instructions file published in the GitHub repository yigitkonur/cli-continues (1,479 stars, last pushed 3mo ago), licensed MIT. It adds 438 tokens to every session, about $0.0022 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
AgentHarbor CLAUDE.md
Instructions for abhiunix/AgentHarbor, covering claude.md, commands, architecture, two tauri windows and adapter trait — the core abstraction.
skills CLAUDE.md
Instructions for lovstudio/skills, covering claude.md, what this is, repo layout, how users install and skills.yaml schema.
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.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
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.