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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/yigitkonur/cli-continues/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/yigitkonur/cli-continues/copilot-instructions.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 | $0.00527 | $0.00527 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
cli-continues copilot-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 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
continues — Code Review Standards
Read-Only Semantics
- Session data is NEVER modified. Any PR that writes to
~/.claude/,~/.codex/,~/.copilot/,~/.gemini/,~/.factory/,~/.cursor/, or~/.local/share/opencode/is a critical bug. - Handoff files (
.continues-handoff.md) write only to the project's own working directory — never to tool storage paths.
ESM Conventions
- All local imports must use
.jsextensions, even for.tssource files:import { foo } from './bar.js' - Never use
require()— this is an ESM-only codebase ("type": "module"inpackage.json) - Use
process.exitCode = Ninstead ofprocess.exit(N)— allows cleanup handlers to run
Error Handling
- Use typed errors from
src/errors.ts(ParseError,SessionNotFoundError,ToolNotAvailableError) for user-facing error paths — not barethrow new Error() - Parsers must silently skip malformed session data with
catch {}— never propagate parse errors to the caller
Registry Completeness
- Every
SessionSourcemember insrc/types/tool-names.tsmust have a registeredToolAdapterinsrc/parsers/registry.ts - The completeness assertion at the bottom of
registry.tsthrows at module load if any adapter is missing — a missing entry crashes the CLI at startup - Adding a tool to
TOOL_NAMESwithout a registry entry is always a bug; changes toSessionSourcerequire coordinated updates in the registry, fixtures, and tests
Code Quality
- Biome handles all formatting and style — do not introduce ESLint, Prettier, or TSLint configs
- No synchronous file I/O (
readFileSync,writeFileSync) in parser code — blocks the event loop when scanning large session directories - Shared helpers
cleanSummary,extractRepoFromCwd, andhomeDirlive insrc/utils/parser-helpers.ts— do not duplicate them in individual parsers
Performance
- Parsers run in parallel via
Promise.allSettledin the session index builder — a slow parser delays only its own results - The session index uses a 5-minute TTL cache at
~/.continues/sessions.jsonl— cache bypasses should be explicitly justified
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 · 35 lines · 527 tokens per session scan A 43e35fb99dba
cli-continues copilot-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 527 tokens to every session, about $0.0026 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).