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/harumiweb/exstruct/adr-governancegit clone --depth 1 https://github.com/harumiWeb/exstructWhat 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 | $0.01274 |
| Opus 5 | $0.00000 | $0.00637 |
| Sonnet 5 | $0.00000 | $0.00255 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
adr-governance 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR governance
This document defines when AI agents should create or update ADRs in ExStruct, and what counts as evidence.
Purpose
- Prevent design decisions that affect long-term maintenance from being buried in issue threads or diffs
- Preserve the responsibility split with
dev-docs/specs/,tests/, andsrc/ - Make the relationship between existing ADRs and new changes explicit, so decision rationale does not go stale
Role of each document
- ADR = why a policy was chosen
- specs = what is guaranteed
- tests = evidence that the guarantee exists
- src = how it is implemented
Do not put implementation notes alone into ADRs. Simple procedures and temporary work order belong in tasks/.
When to create a new ADR
Prefer a new ADR when any of the following apply:
- adding a new policy or responsibility boundary
- introducing a decision on a different issue that existing ADRs cannot explain
- comparing multiple options or accepting a long-term trade-off
- addressing a question that may recur in the future
When to update an existing ADR
Prefer updating an existing ADR when all of the following are true:
- the existing ADR's policy remains intact, but its context, evidence, or related specs should be strengthened
- the same issue covered by the existing ADR gains additional evidence or clarifying constraints
- implementation or documentation cleanup only requires references to be refreshed
If the conclusion of the ADR itself changes, consider a new ADR plus supersede instead of an update.
Handling supersedes
- If the old ADR no longer has authority, create a new ADR and mark the old ADR as
superseded - Update both
Superseded byon the old ADR andSupersedeson the new ADR - Do not do partial overwrite without stating which policy was replaced
Evidence requirements
An ADR must have at least one piece of concrete evidence.
- Tests: regression tests, contract tests, integration tests
- Code: key files that implement the decision
- Related specs: internal specs or public docs that define the current contract
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 · 123 lines · 0 tokens per session scan A c489195428e7
adr-governance is an agent published in the GitHub repository harumiWeb/exstruct (196 stars, last pushed 2mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 1,274 tokens. 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 agents, from other repositories
ai-chat
AI 对话编排领域。任务涉及编排器 AgentOrchestrator、ToolRegistry、SSE 事件流、上下文组装、记忆系统、MCP、子 Agent、模型路由、回放评测时，先读本文档再动代码。.
ai-doc-bridge
AI↔文档编辑桥接领域。任务涉及 doc/sheet/slide 编辑原语、EditorBridgeService、editorcommand 契约、修订（redline）、文档检查点、EDITORACTIONS/uicommand 白名单时，先读本文档再动代码。.
licensing-billing
授权与计费领域。任务涉及解锁门（试用码/账户 Key）、与官网账户的连接、entitlement 权益判定、免费额度与付费解锁、平台 AI 通道计费、广场付费项闸门、本机免登身份解析时，先读本文档再动代码。.
office-addin
Microsoft Office 与 WPS 插件领域。任务涉及 Word/Excel/PPT 任务窗格插件（office-addin/）、manifest、Office.js、WPS 加载项（wps/ 壳、wpsExecutor、publish 安装页）、插件与后端的对话/上下文契约、sideload 调试时，先读本文档再动代码。.
version-control
项目级版本记录领域。任务涉及版本记录/工作段（work session）、时间线、退回版本、丢弃工作、另起一稿/多稿并行/采纳-放弃-冲突三选一、项目 Git 仓库（com.checkba.version 包）、文件树清单 .awd/tree.json 时，先读本文档再动代码。.
sidebar-shell
侧边栏与工作台外壳领域。任务涉及左侧 rail/左栏、工作台四列布局、面板切换、页面路由与页面栈、设置入口、project-overview.vue 结构、CSS 体系时，先读本文档再动代码。.