Ouroboros is a general-purpose AI agent that maintains its identity, memory, and task history across restarts while working on external projects and coordinating specialist agents. It runs as a desktop application or headless command-line tool, using configured remote APIs or a local model for inference. The catalogue skills support working with or modifying Ouroboros.
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/razzant/ouroboros/telegramnpx skills add razzant/ouroboros --skill telegramgit clone --depth 1 https://github.com/razzant/ouroborosWrote 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/razzant/ouroboros/telegram)<a href="https://agentmods.dev/skills/razzant/ouroboros/telegram"><img src="https://agentmods.dev/badge/skills/razzant/ouroboros/telegram.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 5.1 | $0.00019 | $0.00604 |
| Opus 5 | $0.00010 | $0.00302 |
| Sonnet 5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
telegram 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 today.
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
One owner-only Telegram integration provides both the established bot bridge and the optional Mini App. The first positive private Telegram chat binds as the sole owner. Text and photos can be sent to Ouroboros; replies, photos, videos, documents, typing state, subagent cards, and opt-in notifications are mirrored back to that owner.
Version 1.1 adds richer Telegram formatting, native MP3/M4A playback, and inline link keyboards.
The Mini App exposes the unchanged Ouroboros SPA through the established owner-authenticated sidecar and a pinned Cloudflare Quick Tunnel. It is enabled by default after owner binding and can be turned off independently without stopping the text bridge. Disabling the skill destroys process-memory Mini App sessions, stops public exposure, and best-effort restores the prior Telegram menu button. Rotate the bot token only while the skill is disabled, then re-enable it.
Set TELEGRAM_BOT_TOKEN in Settings, grant it to this skill, enable the skill,
and send the bot a private message to bind the owner. No legacy Telegram skill
state is copied or changed. Installations that use telegram-bridge or
telegram-miniapp-poc must disable or remove those skills before enabling this
one.
The Mini App supports macOS arm64/x86_64, Linux arm64/x86_64, and Windows x86_64. Only the explicit unsupported OS/architecture case degrades independently: the text bridge remains available while Mini App status reports that no pinned cloudflared asset exists. Invalid host runtime, unsafe state, or companion registration errors fail the skill load instead of claiming a partial healthy installation.
The Mini App is Beta. Its best-effort Cloudflare Quick Tunnel has no SLA and does not support Server-Sent Events (SSE). It targets native Telegram clients; Telegram WebA/WebK are not supported.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- lib/miniapp_registration.py 8.6 KB runs code
- lib/telegram_api.py 40 KB runs code
- lib/telegram_health.py 6.2 KB runs code
- lib/telegram_notifier.py 9.5 KB runs code
- lib/telegram_state.py 10 KB runs code
- plugin.py 62 KB runs code
- scripts/cloudflare_tunnel.py 33 KB runs code
- scripts/companion.py 54 KB runs code
- scripts/platform_support.py 12 KB runs code
- scripts/public_gateway.py 14 KB runs code
- scripts/runtime_status.py 5.8 KB runs code
- scripts/sidecar.py 40 KB runs code
- scripts/telegram_menu.py 17 KB runs code
- scripts/telegram_settings.py 4.7 KB runs code
- scripts/tunnel_watchdog.py 1.8 KB runs code
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.
- today Changed · +3 lines 9fe4c7ba3158
- 6d ago First seen · 55 lines · 19 tokens per session scan A f0e5caeb5f53
telegram is a skill published in the GitHub repository razzant/ouroboros (1,265 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 604 once invoked, about $0.0001 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
data-analysis
Analyze, explore, clean, and visualize datasets with statistical rigor. Use when user asks to analyze data, find patterns, compute statistics, create visualizations, clean messy data, or explore a dataset. Trigger when user says things like "analyze this data", "what trends do you see", "find patterns in", "create a…
summarization
Summarize documents, articles, conversations, code, and technical content into concise, accurate summaries. Use when user asks to summarize, condense, create a TL;DR, write an executive summary, extract key points, or distill content. Trigger when user says things like "summarize this", "give me the key points"…
experiment_management
Set up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown).
evaluate
Compare baseline and new implementation results. Produce the machine-readable final report result.json, update experiments.json, and append a row to comparison.json.
implement
Create a new Jupyter notebook implementing the method from the research paper, using the same data as the baseline. Record implementation details and measured metrics as a structured JSON entry.
progress
Maintain a machine-readable progress file so dashboards, CLIs, and notebooks can poll the experiment's state at any time. The file is a JSON document — never markdown, never human-prose-first.