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/leynier/telegram-cli/agents-mdgit clone --depth 1 https://github.com/leynier/telegram-cliWhat 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 | $0.00526 | $0.00526 |
| Opus 5 | $0.00263 | $0.00263 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
telegram-cli 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 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
Build and maintain clitg as a deterministic, non-interactive Telegram CLI for AI agents. Treat
its stdout JSON, schemas, exit codes, safety checks, and capability manifest as public APIs.
Tooling
- Use uv for all Python and dependency operations.
- Create project metadata with
uv init; add or remove dependencies withuv addanduv remove. - Commit
uv.lockand.python-version. Do not hand-edit dependency arrays. - Run Python commands through
uv run. - Use Ruff for formatting and linting, and ty for type checking.
- Write code, comments, documentation, tests, and commit messages in English.
Product invariants
- Never add interactive prompts. All values must arrive through options, environment variables, files, or explicitly selected stdin.
- Emit operational successes and failures as schema-versioned JSON or JSONL on stdout.
- Keep stderr empty unless redacted verbose diagnostics were explicitly requested.
- Never print or log API hashes, login codes, passwords, auth keys, or session material.
- Do not mark messages read during list, get, search, resolve, schema, or capability operations.
- Resolve ambiguous peers by returning candidates; never guess a mutation target.
- Support
--dry-runfor every mutation. Preserve exact confirmation and critical-token checks. - Treat unknown raw methods as critical until their risk has been reviewed.
- Keep personal sessions, credentials, Telegram data, and real account identifiers out of tests.
Architecture
- Keep Typer presentation, application services, storage, and Telethon integration separated.
- Keep Telethon and dynamic TL values at adapter boundaries; use typed Pydantic models internally.
- Prefer the friendly Telethon API for dedicated commands and the generated TL registry for raw coverage.
- Update generated schemas and capabilities whenever public models or Telethon change.
- Preserve schema
0.2across patch releases. A breaking contract requires a new minor schema and a coordinated skill update.
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 · 50 lines · 526 tokens per session scan A ee81727cbc11
telegram-cli AGENTS.md is an instructions file published in the GitHub repository leynier/telegram-cli (8 stars, last pushed 2d ago), licensed MIT. It adds 526 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 2026-08-31.
Other instructions, from other repositories
antigravity-testing-kit GEMINI.md
Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
free-ai-gateway AGENTS.md
Instructions for zaber-dev/free-ai-gateway, covering 🤖 free-ai gateway - agentic development guidelines, 🏛️ monorepo architecture & package boundaries, 🛑 strict architectural rules for agents, 💻 essential developer commands and build all packages across monorepo.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.