analysis-dr

analysis-dr is a command for coding agents from with-geun/alive-analysis. It costs 0 tokens per session (1,828 once invoked), scanned A, original, MIT.

A command for managing Analysis Decision Records, which are an append-only log of decisions about how a team performs analysis.

In plain words
What is it for?
Use it to create, scan for, list, or display analysis decision records with the commands `new`, `scan`, `list`, and `show`.
Why use it?
It keeps methodology choices documented and helps prevent repeated or conflicting decisions across analyses.

Command

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/with-geun/alive-analysis/analysis-dr
Clone the repo
git clone --depth 1 https://github.com/with-geun/alive-analysis

Wrote 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.

agentmods badge for analysis-dr

README.md
[![agentmods](https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-dr.svg)](https://agentmods.dev/commands/with-geun/alive-analysis/analysis-dr)
Your own site
<a href="https://agentmods.dev/commands/with-geun/alive-analysis/analysis-dr"><img src="https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-dr.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,828 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 $0.00000 $0.01828
Opus 5 $0.00000 $0.00914
Sonnet 5 $0.00000 $0.00366
Haiku 4.5 $0.00000 $0.00183

Measured 4d ago against content hash 52eb887db423, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analysis-dr 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.

platforms/claude-code/commands/analysis-dr.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/analysis-dr

Manage Analysis Decision Records — the team's append-only log of methodology decisions.

Subcommands: new | scan | list | show {NNN}

Instructions

Step 1: Parse subcommand

Read $ARGUMENTS:

  • new or no argument → write a new DR (go to Step 2a)
  • scan → scan analyses for DR candidates (go to Step 2b)
  • list → display the DR index (go to Step 2c)
  • show {NNN} → display a specific DR (go to Step 2d)

If argument is ambiguous, default to new.


Step 2a: New DR

Goal: Help the user write a well-formed DR, or propose one based on current context.

Step 2a-1: Load context

Read these files to understand what might need a DR right now:

  • .analysis/config.md — current metrics, team context
  • .analysis/status.md — active analyses
  • For each active analysis folder, read its most recent stage file (e.g., 03_investigate.md if at INVESTIGATE)
  • analyses/decisions/INDEX.md — existing DRs (to avoid duplicates)

Step 2a-2: Check for decision signals

Look for signals that a decision was made or is being debated:

  • Metric being defined or redefined in the current analysis
  • Statistical method chosen (A/B test, regression, etc.)
  • Segment or time window that was argued about
  • Model algorithm that was selected over alternatives

If strong signals found, propose a DR draft:

📋 DR 초안 제안

분석에서 다음 결정이 발견됐어요. DR로 기록하면 좋을 것 같아요:

유형: {Metric | Methodology | Scope | Model | Principle}
제목 초안: "{결정 제목}"
결정 내용: "{한 문장 초안}"

이대로 작성할까요, 아니면 직접 내용을 알려주세요?

If no strong signals, ask the user:

어떤 결정을 DR로 남기고 싶으세요?
유형을 알려주시면 해당 템플릿으로 안내해드릴게요:
  Metric — 지표 정의
  Methodology — 분석 방법론
  Scope — 세그먼트/기간 범위
  Model — 모델/알고리즘 선택
  Principle — 분석 원칙

Step 2a-3: Determine next DR number

Read analyses/decisions/INDEX.md. Count existing DRs and increment by 1 (e.g., if DR-005 is last → new DR is DR-006). If INDEX.md doesn't exist yet, start with DR-001.

Step 2a-4: Write the DR

Collect or confirm these fields with the user:

  • 결정: one sentence, what was decided
  • 배경: what triggered this decision
  • 근거: why this choice, what alternatives were rejected
  • 트레이드오프: what costs are accepted
  • 검토 트리거: when to reconsider
  • 참고 분석: analysis folder path (optional)

Read the full file on GitHub · 234 lines

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. 4d ago First seen · 234 lines · 0 tokens per session scan A 52eb887db423

Subscribe to this mod's changes

analysis-dr is a command published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,828 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.