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/claude89757/wechat-on-airflow/agents-mdgit clone --depth 1 https://github.com/claude89757/wechat-on-airflowWrote 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/claude89757/wechat-on-airflow/agents-md)<a href="https://agentmods.dev/instructions/claude89757/wechat-on-airflow/agents-md"><img src="https://agentmods.dev/badge/instructions/claude89757/wechat-on-airflow/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 5.1 | $0.02040 | $0.02040 |
| Opus 5 | $0.01020 | $0.01020 |
| Sonnet 5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
wechat-on-airflow 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 yesterday.
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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
This repository is operated primarily by coding agents. Treat repository content and production read-only checks as the source of truth. Do not rely on chat history for operational knowledge.
Mission
Run the production Shenzhen tennis availability platform on Apache Airflow 3 with PostgreSQL-owned subscriptions and notification state, host-owned Tencent SES delivery, best-effort WeChat delivery through the Android sender, deterministic verification, and reversible exact-commit deployments.
For repository-wide diagnosis, operations, incident response, release, or
deployment work, load
.agents/skills/operate-tennis-alerts/SKILL.md and follow its lifecycle.
Read First
config/active-components.yamlconfig/config-contracts.yamlconfig/host-core-contract.yamlconfig/runtime-target.yamlARCHITECTURE.mddocs/production-baseline.md- Relevant runbooks and ADRs
On every resumed task, inspect the current Git worktree, pushed commit, existing verification evidence, and production baseline before changing files. Continue from the last verified state; chat history is not authoritative.
Repository Boundaries
dags/: production DAG definitions and task wiring only.src/wechat_airflow/venues/: venue API, parsing, filtering, and observation orchestration.src/wechat_airflow/host_core/: the PostgreSQL-backed Web API, migration, matching, email delivery, delivery reconciliation, and durable notification workers.src/wechat_airflow/notifications/: Airflow observation client, WeChat client, booking-link policy, and channel-specific compatibility helpers.src/wechat_airflow/proxy_tools/: proxy refresh implementations.src/wechat_airflow/maintenance/: device maintenance implementations.tests/: unit, contract, DAG import, migration, and smoke tests.config/: non-secret machine-readable contracts.scripts/: idempotent development and operations commands.pi_host/: Raspberry Pi scrape-host services, not Airflow DAG code.webapp/: React assets and the stateless Cloudflare edge gateway. Legacy D1 code is retained only for the migration and rollback window.docker/: reproducible Airflow and service image files.docs/: architecture, runbooks, configuration, decisions, and evidence.
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.
- yesterday Changed · +20 lines · +326 tokens per session b65f5a2744b9
- 5d ago First seen · 195 lines · 1,714 tokens per session scan A 20ba6b91f255
wechat-on-airflow AGENTS.md is an instructions file published in the GitHub repository claude89757/wechat-on-airflow (90 stars, last pushed today), licensed MIT. It adds 2,040 tokens to every session, about $0.0102 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
airflow AGENTS.md
AGENTS.md instructions for apache/airflow, covering agents instructions, naming, environment setup, commands and repository structure.
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
lobu AGENTS.md
AGENTS.md instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.