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/far-se/tabame/agents-mdgit clone --depth 1 https://github.com/Far-Se/tabameWhat 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 | $0.00229 | $0.00229 |
| Opus 5 | $0.00114 | $0.00114 |
| Sonnet 5 | $0.00046 | $0.00046 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
tabame 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 2d 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
Dart validation
After editing Dart files, from the project root, using dart as resolved from PATH:
dart format <changed-files>
dart analyze <changed-files>
Never: invoke dart.bat/flutter.bat (even via absolute path), invoke Dart by absolute path, modify/reconstruct PATH, use the Dart MCP dart_format tool, or run flutter build/flutter run.
Never run any building commands like flutter build windows if you havent changed CPP/H code.
Never run flutter test or any form of tests.
If you modified some code that has a _test.dart file, only run that.
Rules: one Dart command at a time; format/analyze only files changed this task; run format once and analyze once (no full-project analysis unless asked); on failure, report the command, the failure, and any output as-is.
Native Feature Implementation
Only implement code for Windows if you need native API/functions and leave a mockup for Linux and Mac with comment //TODO: Implement multiplatform
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.
- 2d ago First seen · 20 lines · 229 tokens per session scan A b7c6ee9d1c17
tabame AGENTS.md is an instructions file published in the GitHub repository Far-Se/tabame (366 stars, last pushed 3d ago), licensed MIT. It adds 229 tokens to every session, about $0.0011 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
nim_duilib CLAUDE.md
Instructions for rhett-lee/nim_duilib, covering nimduilib - 跨平台 c++ ui 库, 项目概述, 项目结构, 开发模式（xml + c++） and xml 布局文件.
mcec AGENTS.md
Instructions for tig/mcec, covering agents.md: driving (and testing) mcec with an agent, the built-in guidance (single source of truth), security (do not regress), dogfood: test mcec using mcec (mcec drives mcec) and operational tips (learned the hard way).
ContextMenuMgr AGENTS.md
AGENTS.md instructions for PLFJY/ContextMenuMgr, covering agents.md, 1. required reading, 2. identify the correct flow before editing, 3. hard rules and user context.
AIUsageTracker AGENTS.md
Instructions for rygel/AIUsageTracker, covering ai usage tracker - monitor guidelines, critical rules, never wipe user settings (critical), never cause data loss in migrations (critical) and never create releases without explicit permission.
AIUsageTracker CLAUDE.md
Instructions for rygel/AIUsageTracker, covering claude.md, build & test, analyzer rules — do not weaken, architecture and data flow: monitor → main window.