safe_wallet AGENTS.md

A set of working instructions for AI agents contributing to the ascenx/safe_wallet codebase. It defines communication, editing, architecture, testing, and Git rules.

In plain words
What is it for?
Use it to guide code changes, tests, documentation updates, and Git operations in the safe_wallet repository.
Why use it?
It gives agents shared boundaries for making safe, focused changes without overwriting people’s work or violating the project’s structure.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/ascenx/safe_wallet/agents-md
Clone the repo
git clone --depth 1 https://github.com/ascenx/safe_wallet

Made for: Codex, OpenCode.

Per session 1,091 This file is loaded in full into every session.
When invoked 1,091 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01091 $0.01091
Opus 5 $0.00545 $0.00545
Sonnet 5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured yesterday against content hash 143f8d72fc59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

safe_wallet 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.

AGENTS.md · 75 lines

What it actually says

AGENTS.md

本文件面向在仓库中工作的所有 AI agent。目标是提供一套通用、稳定、可执行的协作规范,减少误改、返工和低质量提交。

如无更高优先级的人类指令,默认遵守本文件。若与用户直接要求冲突,以用户要求为准。

1. 沟通原则

  • 回复应直接、具体、可执行,避免空泛总结。
  • 先理解需求,再行动;不要凭印象修改代码或文档。
  • 如果存在不确定性,优先通过阅读代码、测试、配置和历史改动获取上下文。
  • 不要把未经验证的推测表述成事实。

2. 工作方式

  • 优先做小而准的改动,避免顺手大改、顺手重构、顺手重命名。
  • 先找根因,再修问题;不要用堆补丁的方式掩盖症状。
  • 涉及行为变更或 bug 修复时,优先先补失败测试,再写实现。
  • 如果用户已经手动改过代码,不要覆盖、回退或重排这些改动。
  • 如果 AI 生成代码后用户又手动修改了相关代码,后续一律以用户手动修改后的版本为准,不要恢复、覆盖或重写回 AI 之前生成的版本。
  • 如果用户手动修改了代码,除非能证明该修改存在 bug,否则对应单元测试应按用户修改后的代码行为同步调整;不要为了让旧测试通过而反向修改或覆盖用户代码。
  • 工作区可能是脏的;除非用户明确要求,否则不要清理与当前任务无关的改动。

3. 代码修改边界

  • 架构实现、模块划分、依赖方向和目录组织必须遵循根目录的 ARCHITECTURE.md;如任务确需调整架构,应先说明原因,并同步更新该文档。
  • UI、交互、视觉样式、设计 Token 和组件使用必须遵循根目录的 DESIGN.md;优先复用已有设计体系,不得自行引入与规范冲突的样式。
  • 不得擅自引入新依赖、升级依赖或替换基础设施,除非用户明确要求。
  • 不要随意改变现有模块的架构风格;优先遵循当前文件和当前模块已有模式。
  • 改动前优先复用现有组件、工具函数、helper、resolver、测试基建和样式体系。
  • 修改应尽量落在根因层,不要只在 UI 或调用层“遮住问题”。
  • 不要因为“顺手”去修改与当前任务无关的文件。

4. Git 规则

  • 未收到用户明确指令时,禁止执行 git commitgit pushgh pr create
  • 禁止使用破坏性命令,例如:
    • git reset --hard
    • git checkout -- <file>
    • 强制回滚或覆盖用户改动
  • 需要提交时,只提交与当前任务相关的文件。
  • 提交前先看 git status,确认本次提交范围准确。

5. Subagent 规则

  • 用户不主动要求时,不要使用 subagent。
  • 不要把“想更快一点”“想并行一点”“想多看几个方向”当成使用 subagent 的理由。
  • 只有当用户明确要求使用 subagent、委派、并行 agent、子代理协作时,才可以使用。

6. 验证要求

  • 不要在没有验证证据的前提下宣称“修好了”“已完成”“可以提交”。
  • 优先运行与改动最相关的定向测试;必要时再扩大验证范围。
  • 如果没有合适的现成测试,至少补最小回归测试,或明确说明为什么无法补。
  • 如果测试或验证没有跑通,必须明确说明:
    • 没跑成什么
    • 为什么没跑成
    • 当前剩余风险是什么

7. 调试要求

  • 先复现或先定位可证明的根因,再修改实现。
  • 多层问题要先梳理数据流:
    • 输入从哪里来
    • 参数如何传递
    • 数据如何转换
    • 最终在哪里展示或生效
  • 连续两三次修补都没解决时,停下来重新审视设计,不要继续堆补丁。

8. 文档与规范维护

  • 如果仓库存在通用协作规范文件,优先维护在根目录,例如 AGENTS.md
  • 如果新增了后续 agent 也需要遵守的重要规则,应同步更新本文件。
  • 本文件应保持通用,不绑定具体业务、具体框架、具体目录结构,除非用户明确要求写成项目定制版。
Changes

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.

  1. yesterday First seen · 75 lines · 1,091 tokens per session scan A 143f8d72fc59

Subscribe to this mod's changes

safe_wallet AGENTS.md is an instructions file published in the GitHub repository ascenx/safe_wallet (135 stars, last pushed 19d ago), licensed MIT. It adds 1,091 tokens to every session, about $0.0055 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.