analysis-journal

analysis-journal is a skill for Claude Code from etoyama/insight-blueprint. It costs 94 tokens per session (2,460 once invoked), scanned A, original, MIT.

A reasoning journal for recording how an analysis develops, including observations, evidence, decisions, questions, and competing explanations.

In plain words
What is it for?
Use it during hypothesis-driven analysis to record findings, choose methods, track questions, and branch between hypotheses.
Why use it?
It keeps the path from evidence to conclusion visible instead of leaving important reasoning scattered or forgotten.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md.

Part of the insight-blueprint plugin — 10 skills, 2 MCP servers shipped together

Good fit Use it during hypothesis-driven analysis to record findings, choose methods, track questions, and branch between hypotheses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/etoyama/insight-blueprint/analysis-journal
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.

Any agent
npx skills add etoyama/insight-blueprint --skill analysis-journal
Clone the repo
git clone --depth 1 https://github.com/etoyama/insight-blueprint

Made for: Claude Code.

Or install insight-blueprint, the plugin that ships this one along with the rest of its 10 skills, 2 MCP servers.

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-journal

README.md
[![agentmods](https://agentmods.dev/badge/skills/etoyama/insight-blueprint/analysis-journal/github.svg)](https://agentmods.dev/skills/etoyama/insight-blueprint/analysis-journal)
Your own site
<a href="https://agentmods.dev/skills/etoyama/insight-blueprint/analysis-journal"><img src="https://agentmods.dev/badge/skills/etoyama/insight-blueprint/analysis-journal/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for analysis-journal

Your own site · 80×15
<a href="https://agentmods.dev/skills/etoyama/insight-blueprint/analysis-journal"><img src="https://agentmods.dev/badge/skills/etoyama/insight-blueprint/analysis-journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00094 $0.02460
Opus 5 $0.00047 $0.01230
Sonnet 5 $0.00019 $0.00492
Haiku 4.5 $0.00009 $0.00246

Measured 9d ago against content hash f4db94384dd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

analysis-journal 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 9d 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.

skills/analysis-journal/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/analysis-journal — Insight Journal Manager

Records the reasoning process behind an analysis design as a structured event journal. Each event captures a discrete reasoning step — observation, hypothesis, evidence, question, decision, reflection, conclusion, or branch.

Based on Narrative Scaffolding (Huang+ IUI 2026) and Sensemaking Loop (Pirolli & Card) frameworks.

When to Use

  • During active analysis: recording what you observed, decided, or discovered
  • When choosing an analysis method or package (e.g., "CausalImpact を使う")
  • When a new question arises during investigation
  • When branching to an alternative hypothesis

When NOT to Use

  • Creating a new design from scratch (→ /analysis-design)
  • Structured reflection and conclusion (→ /analysis-reflection)
  • Registering data sources or knowledge (→ /catalog-register)

Workflow

Step 1: Identify Target Design

If $ARGUMENTS contains a design ID (e.g., "FP-H01"), use it directly. Otherwise, call list_analysis_designs(status="analyzing") and ask user to select.

Validate with get_analysis_design(design_id).

Step 2: Load or Initialize Journal

Read .insight/designs/{design_id}_journal.yaml using the Read tool.

  • If exists: load and show summary (event count, last 3 events, open questions)
  • If not exists: create with initial structure using the Write tool:
metadata:
  design_id: "{design_id}"
  created_at: "{now in ISO 8601 JST}"
  updated_at: "{now in ISO 8601 JST}"
events: []

Step 3: Record Events (Interactive Loop)

Listen to user input and classify into InsightType:

User says... InsightType Example content
データを見たら〜 / 〜が見えた / 〜に気づいた observe "2026年1月以降、売上が前年比15%低下"
〜だと思う / 仮説: / 〜が原因では hypothesize "価格改定(+8%)が売上低下の主因"
〜で確認した / データが示す / 〜のエビデンス evidence "回帰分析でp<0.01の有意な負の相関"
〜が気になる / 〜を調べたい / なぜ〜 question "季節要因を除外できているか?"
〜を使う / 〜で分析する / 手法: decide "CausalImpact で因果効果を推定する"
振り返ると / 見直すと / 反省点 reflect "初期の相関分析では交絡が未考慮だった"
結論: / まとめると / 〜と言える conclude "価格改定は売上低下の主因と確認"
別の仮説 / 分岐したい / fork branch → Step 4 (Branch Workflow)

Read the full file on GitHub · 236 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. 9d ago First seen · 236 lines · 94 tokens per session scan A f4db94384dd6

Subscribe to this mod's changes

analysis-journal is a skill published in the GitHub repository etoyama/insight-blueprint (0 stars, last pushed 17d ago), licensed MIT. It adds 94 tokens to every session and 2,460 once invoked, about $0.0005 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.