What is spark-telegram-bot CLAUDE.md?

Repository instructions for the spark-telegram-bot, which handles Telegram messages, command routing, access prompts, replies, and connections to other Spark components.

Use them when modifying Telegram input handling, access checks, message delivery, reply formatting, relay metadata, or thin adapters to Builder, CLI, Spawner, memory, and voice systems.

They clarify which behavior this repository owns and which responsibilities belong to other services, reducing changes in the wrong place.

How vibeforge1111/spark-telegram-bot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to vibeforge1111/spark-telegram-bot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vibeforge1111/spark-telegram-bot/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/vibeforge1111/spark-telegram-bot

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vibeforge1111/spark-telegram-bot/claude-md/github.svg)](https://agentmods.dev/instructions/vibeforge1111/spark-telegram-bot/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vibeforge1111/spark-telegram-bot/claude-md"><img src="https://agentmods.dev/badge/instructions/vibeforge1111/spark-telegram-bot/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vibeforge1111/spark-telegram-bot/claude-md"><img src="https://agentmods.dev/badge/instructions/vibeforge1111/spark-telegram-bot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,131 This file is loaded in full into every session.

When invoked 3,131 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 94% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.03131	$0.03131
Opus 5.5	$0.01252	$0.01252
Sonnet 5.5	$0.00626	$0.00626
Haiku 4.5	$0.00313	$0.00313

Measured 2mo ago against content hash a383b18b2a3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spark-telegram-bot CLAUDE.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 2mo 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.

Origin

This is a copy

94% identical to spark-telegram-bot AGENTS.md — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spark Telegram Bot Agent Ruleset

Repo Role

spark-telegram-bot owns Telegram ingress, concise user-facing composition, command routing, delivery, access prompts, relay metadata, and thin adapters to Builder, CLI, Spawner, memory, and voice evidence.

Canonical truth owned here:

Telegram command and natural-language ingress behavior
Telegram-specific access prompts, chat delivery, and reply composition
relay metadata and metadata-only audit rows emitted by the Telegram adapter
thin route-context serialization for Builder-owned gates
Telegram-facing rendering of Builder/CLI/Spawner/Cockpit evidence

This repo does not own:

Builder RouteConfidenceGateV1, AOC, identity, or memory orchestration
durable memory storage, memory proof-card truth, or memory mutation authority
CLI registry, installer, secret storage, or module lifecycle
Spawner mission execution or provider output bodies
Cockpit UI action authority or dashboard truth

Start-of-Work Protocol

Run git status --short --branch.
Read this file plus docs/SPARK_SYSTEM_GOVERNANCE_RULESET.md, docs/SPARK_HUMAN_CONVERSATION_QA_MAP.md, docs/SPARK_AGENT_USAGE_RESEARCH_HERMES_OPENCLAW_2026-06-16.md, docs/TURNINTENT_HARNESS_RULESET.md, and the relevant command, route, or adapter doc before edits.
Identify whether the change is Telegram-owned or belongs in Builder, CLI, Spawner, memory, Cockpit, voice, Labs, or Swarm.
Define the smallest user-visible behavior and stop-ship gate.
Add focused tests for routing, composition, access, bridge serialization, or relay metadata.
Keep adapters thin and metadata-only.
Commit one logical checkpoint and record verification.

Spark-Wide Root-Cause Governance

The canonical repo rule is docs/SPARK_SYSTEM_GOVERNANCE_RULESET.md.

Do not patch Spark behavior with deterministic phrase saves, exact project-name special cases, exact mission-id handling, or reply-text fixes that only make the latest transcript look good. For every nontrivial Spark fix, classify the failure family, identify the earliest owning layer, and prove one natural positive plus one adjacent negative trap.

Read the full file on GitHub · 243 lines

Changes

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.

2mo ago First seen · 243 lines · 3,131 tokens per session scan A a383b18b2a3f

Subscribe to this mod's changes

spark-telegram-bot CLAUDE.md is an instructions file published in the GitHub repository vibeforge1111/spark-telegram-bot (2 stars, last pushed 2mo ago), licensed MIT. It adds 3,131 tokens to every session, about $0.0125 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to spark-telegram-bot AGENTS.md, differing in 3 lines, and is treated as a copy.

spark-telegram-bot CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spark-telegram-bot CLAUDE.mdvibeforge1111/spark-telegram-bot	Instructions file	2	2mo ago	MIT	A	3,131	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

spark-telegram-bot: Instructions file for Claude Code