adr

A command that creates an Architecture Decision Record, or ADR: a short document explaining an important technical choice, its alternatives, consequences, and current status.

In plain words
What is it for?
Use it to extract genuine architecture decisions from a session and document the chosen approach, rejected options, trade-offs, and expected effects.
Why use it?
It preserves why a design decision was made, so the reasoning is available later instead of being lost in the coding session.

Command

Part of the tokenknows plugin — 2 skills, 9 commands, 1 MCP server shipped together

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 commands/johnnywuj81/tokenknows/adr
Clone the repo
git clone --depth 1 https://github.com/johnnywuj81/tokenknows

Or install tokenknows, the plugin that ships this one along with the rest of its 2 skills, 9 commands, 1 MCP server.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 243 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00041 $0.00243
Opus 5 $0.00020 $0.00121
Sonnet 5 $0.00008 $0.00049
Haiku 4.5 $0.00004 $0.00024

Measured 2d ago against content hash 56db5891c512, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adr 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.

tokenknows-plugin/commands/adr.md · 17 lines

What it actually says

tokenknows:distill skill 的标准流程,把当前 session 蒸馏成 adr:

ADR 关键特征:

  • 必须有 明确决策点 (e.g. "用 React Flow 而非 G6 做 KG 可视化")
  • 必须有 备选方案 + 取舍理由
  • 不是流水, 是 "为什么这么选" 的浓缩
  1. 检查 session 里是否有真实架构决策; 没有就告诉用户 "这次 session 没有明显架构决策, 建议改用 weekly_report"
  2. 拆 event 聚焦决策点 (备选 N 个 / 选了 X / 因为 Y / 后果 Z)
  3. submit_session_events
  4. distill_document(document_type="adr") ← 注意 ADR 时间窗一般不重要
  5. 展示
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. 2d ago First seen · 17 lines · 41 tokens per session scan A 56db5891c512

Subscribe to this mod's changes

adr is a command published in the GitHub repository johnnywuj81/tokenknows (4 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 243 once invoked, about $0.0002 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 2026-08-31.