Borrowing it
Nothing to install: this file belongs to Divkix/Alita_Robot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Divkix/Alita_Robot/main/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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.02839 | $0.02839 |
| Opus 5.5 | $0.01136 | $0.01136 |
| Sonnet 5.5 | $0.00568 | $0.00568 |
| Haiku 4.5 | $0.00284 | $0.00284 |
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 3d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Alita Robot: Telegram group-management bot. Go module github.com/divkix/Alita_Robot; PostgreSQL (GORM) + Redis.
This file holds only rules that span packages. A rule about one package lives in the doc comment of that package
or of the symbol it governs, so it changes in the same diff as the code: read the doc comments of the files you
touch, and put a new package rule there. internal/agentsmd fails make test when a name or path in this file no
longer exists, or when the file outgrows its budget.
Product
- Additive by default: a new feature leaves what existing commands, settings and defaults do unchanged.
- New behaviour a chat can see (spam checks, captcha, auto-actions) ships off and is enabled per chat.
- Change an existing default or command meaning only to fix a bug; commit it as
fix:with the old and new behaviour in the body. - Group-only and connection-based usage keep working when a PM or shortcut form is added.
- In PM a group the user names wins over the connected group. A command without arguments of its own
(
PMGroupArgNone) whose first word does not name exactly one group refuses (its help, the matching groups, orsettings_picker_wait) and never falls back to the connection: the connection is invisible when the message is sent, and acting in the wrong group is worse than a refusal that costs one retry. Mechanics:withPMGroupArg. - A PM reply about a group names it: end the text with
withGroupLine.
Commands
make test # the only valid full run: tags, race, coverage, skip gate
make lint # golangci-lint v2 over the whole tree (.golangci.yml); CI also gates new code on dupl/gocyclo
make nilaway # nil-panic analysis; no suppression comments exist, so make the nil flow explicit
make check-translations # missing locale keys and values copied from en.yml
make generate-docs # after changing en.yml help/*_docs, config.yml alt_names, or command/lock tables
make check-formal # TLC on formal/ (Docker)
make bump-version TAG=vX.Y.Z # the only way to change version strings
go test -tags testtools -race -count=1 -run '^TestName$' ./alita/db/warns # one test
CGO_ENABLED=0 go build ./... # compile check
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.
- 3d ago Changed · -132 lines · -3,715 tokens per session 98a9869c6c91
- 6d ago Changed · +12 lines · +339 tokens per session 2c2b854a1da6
- 7d ago Changed · +99 lines · +2,605 tokens per session c8ba7dd7a89f
- 8d ago Changed · +9 lines · +105 tokens per session 15415e801ab7
- 9d ago Changed · +5 tokens per session ea64639aefa9
- 10d ago Changed · +16 lines · +474 tokens per session b07e3d3bc136
- 11d ago Changed · +9 lines · +225 tokens per session b8061332e097
- 12d ago Changed · +17 lines · +434 tokens per session d1c880752e88
- 13d ago Changed · +2 lines · +51 tokens per session 9d236485447d
- 25d ago First seen · 136 lines · 2,316 tokens per session scan A 7fd5b3b333fb
Alita_Robot AGENTS.md is an instructions file published in the GitHub repository Divkix/Alita_Robot (253 stars, last pushed yesterday), licensed MIT. It adds 2,839 tokens to every session, about $0.0114 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.