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 agents/camellia2077/flipbits/geminigit clone --depth 1 https://github.com/camellia2077/FlipBitsWrote 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/agents/camellia2077/flipbits/gemini)<a href="https://agentmods.dev/agents/camellia2077/flipbits/gemini"><img src="https://agentmods.dev/badge/agents/camellia2077/flipbits/gemini.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 | $0.00000 | $0.00770 |
| Opus 5 | $0.00000 | $0.00385 |
| Sonnet 5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
GEMINI 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.
This is a copy
95% identical to AGENTS — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Terminal
- 在这个仓库执行终端命令时，统一使用
pwsh作为 shell 入口。 - 在这个仓库执行终端命令、编译或验证时，默认不要使用沙盒环境；尤其是
CMake/Ninja/Gradle/python tools/run.py verify相关命令，必须在非沙盒环境执行。
Tooling
- 这个项目的 Python CLI 采用“主命令 / 子命令”分层形式。
- 先用
python tools/run.py --help查看主命令组；需要具体参数时，再用python tools/run.py <command> --help或python tools/run.py <command> <subcommand> --help下钻。 - 常用命令组优先记这几个：
build、test、test-lib、verify、cli、windows、android、android-translate、artifact、history、message - 修改代码后，如需开始编译，优先使用
python tools/run.py build --build-dir build/dev。 - 修改代码后，如需完整验证，优先使用
python tools/run.py verify --build-dir build/dev。 - 修复 review findings 或小批量跨层改动后，可先跑较短验证：
python tools/run.py verify review-fixes --build-dir build/dev。 - 如需只跑库级单测，优先使用
python tools/run.py test-lib <audio_runtime|audio_api|audio_io> --build-dir build/dev。 - 新增 Android XML 文案 key 时，优先用
python tools/run.py android strings-add --file <strings_*.xml> --key <name> --en "<English text>"，避免漏掉本地化目录。 - 不再依赖根层
ctest -R runtime_tests|api_tests|unit_tests作为正式工作流。 - Python CLI 的
--help保持分层：根命令只展示主要子命令与简短摘要，详细参数放到python tools/run.py <command> --help，不要把所有选项堆到顶层帮助里。 - 如需生成或导出可见产物，优先先看
python tools/run.py artifact --help。 - 如需处理 release history，优先先看
python tools/run.py history --help。 - 如需准备 git commit message，优先先看
python tools/run.py message --help，并默认走“先 history、后 message”的链路。 agents/AGENTS.md只保留总原则与高频入口；工具细节统一看<repo-root>/tools/README.md，专题流程统一看<repo-root>/docs/notes/tooling-overview.md。
Subsystems
- Android 相关入口与编译/测试命令看
<repo-root>/apps/audio_android/AGENTS.md。 - CLI 相关入口与编译/测试命令看
<repo-root>/apps/audio_cli/AGENTS.md。 libs/相关入口、扫描策略与模块级文档指向看<repo-root>/libs/AGENTS.md。
Temp Files
- 根目录
temp/是临时文件夹，默认不会被 Git 跟踪。 - 如需生成临时分析、草稿、阶段文档或中间产物，统一放到仓库根目录的
temp/下，不要散落到其他目录。
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 · 33 lines · 0 tokens per session scan A 447cb254e7cc
GEMINI is an agent published in the GitHub repository camellia2077/FlipBits (46 stars, last pushed 25d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 770 tokens. A static security scan graded it A with 0 findings. It is 95% identical to AGENTS, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
artist
Game artist. Generates and processes visual assets, registers them in manifest.json.
architect
Technical architect for one code task. Owns deep technical research, task-level implementation planning, and per-task context configuration.
auditor
Static quality auditor for one code task. Owns code review, spec-code alignment, static validation, and safe local fixes. Does not run the game.
mobile-developer
Cross-platform mobile development specialist for React Native and Flutter. Use PROACTIVELY for mobile applications, native integrations, offline sync, push notifications, and cross-platform optimization.
p1-research-orchestrator
Phase 1 research pipeline orchestrator. Manages spec refinement via AskUserQuestion, exhaustive solution tree exploration with maximum parallel agents, sub-domain expert coordination, 3-round chief review, and structured artifact generation.
p3-uarch-orchestrator
Phase 3 μArch design pipeline orchestrator. Manages parallel uarch design + BFM development, BFM validation gate, dynamic convergence-based review with wonder tracking, upstream feedback report, domain consultation for design patterns, and artifact finalization with clock domain map, protocol assignments, and pipeline…