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 skills add matteblack9/coding-agent-fabric --skill connect-telegramgit clone --depth 1 https://github.com/matteblack9/coding-agent-fabricWrote 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/skills/matteblack9/coding-agent-fabric/connect-telegram)<a href="https://agentmods.dev/skills/matteblack9/coding-agent-fabric/connect-telegram"><img src="https://agentmods.dev/badge/skills/matteblack9/coding-agent-fabric/connect-telegram/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/skills/matteblack9/coding-agent-fabric/connect-telegram"><img src="https://agentmods.dev/badge/skills/matteblack9/coding-agent-fabric/connect-telegram.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 | $0.00030 | $0.00720 |
| Opus 5.5 | $0.00012 | $0.00288 |
| Sonnet 5.5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade C, and why
connect-telegram scanned grade C 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 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
### 3. Collect Credentials How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
connect-telegram
When To Use
- The user wants to connect Telegram to the orchestrator
- Telegram credentials are missing or need rotation
channels.telegram.enabledmust be enabled inorchestrator.yaml
Runtime Adaptation
claudeRead this file first, then useCLAUDE.mdor.claude/only as extra repo context.cursorFollow this file first, then apply.cursor/rules,AGENTS.md, andCLAUDE.mdif they add repo-specific policy.codexTreat this file as the main Telegram setup checklist.opencodeFollow this file first, then layerAGENTS.mdand any OpenCode-only overrides on top.
Rules
- Never overwrite existing Telegram credentials without confirmation
- Present detected values as numbered choices where possible
- Store credentials under
ARCHIVE/telegram/credentials - Empty
allowed_usersmeans the bot accepts all reachable Telegram users
Procedure
1. Verify Orchestrator
Check that orchestrator.yaml exists. If not, stop and run the setup-orchestrator skill first.
Resolve ARCHIVE_PATH from orchestrator.yaml, then inspect whether ARCHIVE/telegram/credentials already exists.
2. Telegram Bot Guide
If the user does not already have a bot token, guide them through BotFather:
1. Open Telegram and search for @BotFather
2. Send /newbot
3. Choose a bot display name
4. Choose a bot username ending in `bot`
5. Copy the full token BotFather returns
3. Collect Credentials
Ask for:
bot_token
allowed_users (optional, comma-separated usernames or numeric user IDs)
Validation rules:
bot_tokenis required and must contain a colonallowed_usersis optional
Summary before writing:
Telegram credentials entered:
bot_token: 123456:...
allowed_users: username1, username2
Save with these values? (yes/no)
4. Save And Configure
Write:
bot_token : 123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11
allowed_users : username1, username2
to:
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 · 121 lines · 30 tokens per session scan C 9510922cfd25
connect-telegram is a skill published in the GitHub repository matteblack9/coding-agent-fabric (2 stars, last pushed 7mo ago), licensed MIT. It adds 30 tokens to every session and 720 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
connect-telegram compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| connect-telegrammatteblack9/coding-agent-fabric | Skill | 2 | 7mo ago | MIT | C | 30 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 529 | 3d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | today | MIT | A | 106 | Claude Code |