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 skills/synaptic-labs-ai/pact-plugin/telegram-guidenpx skills add Synaptic-Labs-AI/PACT-Plugin --skill telegram-guidegit clone --depth 1 https://github.com/Synaptic-Labs-AI/PACT-PluginWrote 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/synaptic-labs-ai/pact-plugin/telegram-guide)<a href="https://agentmods.dev/skills/synaptic-labs-ai/pact-plugin/telegram-guide"><img src="https://agentmods.dev/badge/skills/synaptic-labs-ai/pact-plugin/telegram-guide.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 | $0.00040 | $0.00417 |
| Opus 5 | $0.00020 | $0.00209 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
telegram-guide 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 5d 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.
What it actually says
Telegram Notifications
Telegram is an optional add-on. Not all PACT users have it installed. Before using any telegram tool, check if it exists in your available tools. If telegram_notify is not listed, do NOT attempt to call it — skip all Telegram functionality silently with no errors or warnings to the user.
How to check: If telegram_notify appears in your tool list, the bridge is active. If not, ignore this entire section.
Available tools (only when bridge is active):
| Tool | Purpose | Blocking? |
|---|---|---|
telegram_notify |
Send one-way notification (completions, deployments, alerts) | No |
telegram_ask |
Ask a blocking question with optional buttons; supports text/voice replies | Yes |
telegram_check_replies |
Poll for queued replies to notifications | No |
telegram_status |
Health check (connection, mode, queue depth) | No |
When to notify (target ~3-5 per session):
- Task or phase completions
- Blockers found or algedonic signals
- PR ready for review or merged
- Deployments pushed
When to use telegram_ask:
- Blocking decisions where user may be away from terminal
- Scope clarifications that can't proceed without input
When to check replies (telegram_check_replies):
- Between tasks or phases — check if user reacted to any notification
- After sending important notifications — user may reply with corrections or new instructions
- Replies include context snippet of the original notification
Multi-session behavior:
- Messages are prefixed with
[ProjectName]for session identification - Multiple sessions coordinate via file-based polling — replies route to the correct session
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.
- 5d ago First seen · 38 lines · 40 tokens per session scan A 9baad3d80ec9
telegram-guide is a skill published in the GitHub repository Synaptic-Labs-AI/PACT-Plugin (71 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 417 once invoked, about $0.0002 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.