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/narumiruna/telegram-bot/agents-mdgit clone --depth 1 https://github.com/narumiruna/telegram-botWrote 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/narumiruna/telegram-bot/agents-md)<a href="https://agentmods.dev/instructions/narumiruna/telegram-bot/agents-md"><img src="https://agentmods.dev/badge/instructions/narumiruna/telegram-bot/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 | $0.00791 | $0.00791 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade B, and why
telegram-bot AGENTS.md scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Preserve restrictive deployment dotenv permissions through `umask 077` and `chmod 600`. How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
Documentation
- Keep
README.mdand.env.examplealigned when changing setup, commands, configuration, or environment variables. - Append exactly one line to
docs/CHANGELOG.mdfor each requested repository change usingYYYY-MM-DD | type(scope): summary (#ref). - Never modify existing
docs/CHANGELOG.mdlines.
Code style
- Target Python 3.14 or newer.
- Use async-first Python and type hints throughout
src/. - Follow Ruff with a 120-character line limit and standard Python naming conventions.
- Keep callbacks small and focused on one Telegram interaction.
Commands
- Run
uv syncto install or reconcile dependencies. - Run
uv run botfrom the repository root with a populated.envto start the bot. - Use
uv run pytest tests/<path>.py -vfor targeted tests. - Run
justfor formatting, linting, type checking, and the coverage test suite. - Run
prek run -afor the complete repository hook set. - For documentation-only changes,
prek run --files <changed-paths>andgit diff --checkare sufficient.
Boundaries
- Preserve both replied and current message text when adding fetched URL content, and treat input as empty only when both blocks are empty.
- Use
reply()for shared Telegram response models and update callers plus awaited test mocks together when changing delivery behavior. - Keep
@safe_callbackcompatible withMessagepassed positionally or through themessagekeyword. - Escape externally sourced TWSE names and symbols before formatting them as Telegram MarkdownV2.
- Persist complete
result.to_input_list()items in per-chat agent memory and rely on process restart to reset memory after tool changes. - Keep the supported
numbalower bound inpyproject.tomland pass Python 3.14 explicitly during deployment sync. - Do not create or push release tags unless explicitly requested because matching tags trigger deployment.
Security
- Keep local secrets in the ignored
.envfile and expose documented placeholders only through.env.example. - Keep tokens and integration credentials out of source, tests, logs, and Git history.
- Preserve restrictive deployment dotenv permissions through
umask 077andchmod 600.
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 First seen · 67 lines · 791 tokens per session scan B 8acf54981804
telegram-bot AGENTS.md is an instructions file published in the GitHub repository narumiruna/telegram-bot (1 stars, last pushed 6d ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.