tele-harness
AGENTS.md1 starsChanged 49 days agoMITView on GitHub
An agentic orchestration harness for architecting, scaling, and maintaining Telegram Bots and Telegram Mini Apps.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- create-db-schemaSkill
- fsm-builderSkill
- i18n-builderSkill
- keyboard-navigatorSkill
- mini-app-builderSkill
- payment-gateway-setupSkill
- setup-webhookSkill
- tg-api-navigatorSkill
- tg-copywriterSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Run /init-bot [LANGUAGE/FRAMEWORK] to bind the tech stack across all configuration files:
- Distinctive: line 32
Use structured body for multi-file changes:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
tele-harness
An agentic orchestration harness for architecting, scaling, and maintaining Telegram Bots and Telegram Mini Apps.
Architecture Map
- System Rules:
.agents/memory/master_protocol.md - Bot Manifest:
.agents/memory/bot_manifest.md - Milestone Tracker:
.agents/memory/progress.md - Sub-Agents:
.agents/agents/tg-architect: System design, database schemas, routing, FSM planning.tg-ux-engineer: Keyboards, Mini App frontends, formatting.tg-sec-auditor: Secret protection, rate limiting, HMAC validation.
- Skills:
.agents/skills/keyboard-navigator: Nested menu trees, pagination rows, and 64-byte callback packing.tg-copywriter: Slop-free conversational copy, mobile viewport budgeting, and command names.create-db-schema: Database modeling and migrations.fsm-builder: Finite State Machine scaffolding.i18n-builder: Multilingual dictionaries and language switching.mini-app-builder: TMA frontend, theme bindings, and HMAC checks.payment-gateway-setup: Native Telegram Stars and provider invoices.setup-webhook: Webhook endpoint security and reverse proxy routes.tg-api-navigator: Framework handler routing patterns.
Initializing Stack
Run /init-bot [LANGUAGE/FRAMEWORK] to bind the tech stack across all configuration files:
- Python:
/init-bot python/aiogram3 - Node.js:
/init-bot nodejs/grammy - Go:
/init-bot go/telebot
Git Commit Protocol
- Imperative mood, <=50 characters subject, no period at line end.
- Use structured body for multi-file changes:
- Changes: exact files modified.
- Context: engineering rationale.
- Next Steps: remaining tasks.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.