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 instructions/sudoskys/telegramify-markdown/agents-mdgit clone --depth 1 https://github.com/sudoskys/telegramify-markdownWrote 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/instructions/sudoskys/telegramify-markdown/agents-md)<a href="https://agentmods.dev/instructions/sudoskys/telegramify-markdown/agents-md"><img src="https://agentmods.dev/badge/instructions/sudoskys/telegramify-markdown/agents-md.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 | $0.00767 | $0.00767 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
telegramify-markdown AGENTS.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
telegramify-markdown Agent Guide
This file routes agent work. It is not a README, tutorial, or changelog.
Task Routing
| Task type | First read | Workflow / skill | Verification gate |
|---|---|---|---|
| Understand purpose | docs/GOAL.md or README.md |
goal and boundary extraction | Restate goal, users, non-goals, unknowns |
| Plan roadmap work | docs/ROADMAP.md |
Flag-based decomposition | Updated Flag set or explicit no-change reason |
| Product/API contract change | docs/prd/README.md |
per-boundary PRD update | Living PRD updated; outcomes and contracts changed, not cutover steps |
| Rich Message support | docs/prd/rich-message.md |
PRD contract + converter implementation | Golden HTML tests, payload tests, pdm run test, and live pdm run test-live-rich before PR |
| Architecture decision | docs/adr/ACTIVE.md |
ADR decision workflow | ADR has invariant, alternatives, verification, and frontmatter.prds when applicable |
| Code change | nearest source file and tests | Python/unittest workflow | Focused tests; broader pdm run test when conversion behavior changes |
| Test strategy | existing tests and failure evidence | testing-methodology |
Risk, oracle, and fidelity are named |
| Telegram API compatibility | official Bot API docs and tests/test_server.py |
research + integration validation | Raw Bot API or wrapper-specific validation when available |
Quick Commands
pdm install
pdm install -G tests
pdm install -G mermaid
pdm run test
pdm run test-rich
pdm run test-live-rich
pdm build
make adr-lint
make adr-index
Project Rules
always:
- Communicate with the user in Chinese and address them as "研究员".
- Route the task before editing.
- Use PDM for project commands. Do not use
pip install -e .or directpython -m unittestfor normal verification. - Understand the pyromark event-stream state machine before changing conversion logic.
- Keep core runtime dependencies minimal. The core converter depends on pyromark; Mermaid rendering uses optional Pillow and aiohttp.
- Preserve all Telegram entity offsets and lengths as UTF-16 code units.
- Add public API docstrings.
- Prefer Chinese comments when comments are needed.
- Do not create a PR for Rich Message changes until
pdm run test-live-richpasses against the real Telegram Bot API withTELEGRAM_BOT_TOKENandTELEGRAM_CHAT_ID.
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.
- 4d ago First seen · 70 lines · 767 tokens per session scan A 4aa0e9524a13
telegramify-markdown AGENTS.md is an instructions file published in the GitHub repository sudoskys/telegramify-markdown (381 stars, last pushed 1mo ago), licensed MIT. It adds 767 tokens to every session, about $0.0038 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 instructions, from other repositories
hongdown AGENTS.md
AGENTS.md instructions for dahlia/hongdown, covering project architecture, initial setup, building, testing and website.
hongdown CLAUDE.md
Claude Code instructions for dahlia/hongdown, a project described as: A Markdown formatter that enforces Hong Minhee's Markdown style conventions.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
easy-notion-mcp CLAUDE.md
Instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
TradingAgents-Telegram CLAUDE.md
Instructions for IvanWng97/TradingAgents-Telegram, covering tradingagents-telegram — architecture reference, layout, architecture (for code reviewers), request lifecycle (manual /watch tap) and state ownership.