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/divkix/alita_robot/agents-mdgit clone --depth 1 https://github.com/Divkix/Alita_RobotWrote 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/divkix/alita_robot/agents-md)<a href="https://agentmods.dev/instructions/divkix/alita_robot/agents-md"><img src="https://agentmods.dev/badge/instructions/divkix/alita_robot/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 5.1 | $0.07802 | $0.07802 |
| Opus 5 | $0.03901 | $0.03901 |
| Sonnet 5 | $0.01560 | $0.01560 |
| Haiku 4.5 | $0.00780 | $0.00780 |
Grade A, and why
Alita_Robot 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 yesterday.
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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Alita Robot — Telegram group-management bot in Go 1.26 / gotgbot/v2 v2.0.0-rc.36.
Features: admin, filters, notes, greetings, antiflood/antiraid/antispam, captcha, warns, locks, backups, connections, reactions, i18n (en/es/fr/hi/ru/pt/id).
CLAUDE.mdandGEMINI.mdare symlinks toAGENTS.md— edit only this file.
0. Maintaining this file
- File is hand-maintained. When you change build, env, routes, DB, or layout — update it in the same commit.
- Record why / gotcha / coupling, not what the code already shows. Be specific: name file/func/env/table.
- Consolidate in place; delete stale notes. One accurate sentence > three vague ones.
- Verify before trusting: if a note names a symbol, confirm it still exists.
1. Mental model
Telegram ──► polling OR webhook /webhook POST
──► ext.Dispatcher (TracingProcessor span per update)
──► handlers by group: -10..-1 interceptors → 0 commands (EndGroups) → 4..11 watchers (ContinueGroups)
──► repo (GORM/Postgres + Redis read-through) → reply via i18n + media
- Config + DB open in
init(), notmain().alita/config→config.AppConfig,alita/db→ Postgres pool. Both no-op for--version/--healthor missing env (so tests can import). Don't move tomain(). - DB:
alita/db/<domain>/repos +alita/db/models/structs.alita/db/db.gois a re-export shim for model types &TEXT..VIDEO_NOTEconstants only — not cache helpers. - Schema source is
migrations/*.sqlviaalita/db/migrations/runner.go, notgorm.AutoMigrate. Tests use SQLiteAutoMigrate(testmain_test.go) — struct↔SQL drift is not caught. - Cache is Redis-only (
eko/gocache+go-redis), nil-safe (nil marshaler → direct DB). - Modules self-register in
init(), load ascending priority; Help loads last (deferred). - Callback data: versioned codec
<namespace>|v1|<url-encoded>capped at 64 bytes — neverstrings.Splitraw data.
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.
- yesterday Changed · -747 lines · -8,893 tokens per session 644db6ecaeb9
- 6d ago First seen · 1,032 lines · 16,695 tokens per session scan A 3090199f8d45
Alita_Robot AGENTS.md is an instructions file published in the GitHub repository Divkix/Alita_Robot (247 stars, last pushed today), licensed MIT. It adds 7,802 tokens to every session, about $0.0390 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
telegram-bot AGENTS.md
Instructions for vendelieu/telegram-bot, covering agents.md, dev environment, testing, project structure and key conventions.
ClaudeBot CLAUDE.md
Claude Code instructions for Jeffrey0117/ClaudeBot, covering claudebot, stack, directory structure, key concepts (details in subdirectory claude.md files) and coding rules.
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
octo-cli CLAUDE.md
Claude Code instructions for Mininglamp-OSS/octo-cli, covering claude.md — octo-cli project instructions, what is octo-cli, architecture, identity model and command structure (12 active domains, 322 operations).
telegram-search copilot-instructions.md
Copilot instructions for groupultra/telegram-search, covering copilot instructions for telegram-search, architecture essentials, dev workflows, conventions and patterns and where to look for examples.
telegram-search AGENTS.md
AGENTS.md instructions for groupultra/telegram-search, covering project coded agent guide, tech stack (by surface), structure & responsibilities, key path index (what lives where) and commands (pnpm with filters).