A quick way to record a note about friction in a coding workflow, such as a skill, rule, or process that caused trouble. The note is appended to a JSON Lines file, a text file with one JSON record per line.

Use it when something in a workflow annoyed you or needs improvement, then return to the task you were doing.

It captures a problem while it is still fresh without opening an editor or interrupting the current work.

kaizen — Skill for Claude Code by digital-stoic-org

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 digital-stoic-org/agent-skills --skill kaizen

Clone the repo

git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install dstoic, the plugin that ships this one along with the rest of its 14 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/kaizen/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/kaizen)

Your own site

<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/kaizen"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/kaizen/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/kaizen"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/kaizen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 723 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 4
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.00723
Opus 5	$0.00051	$0.00362
Sonnet 5	$0.00020	$0.00145
Haiku 4.5	$0.00010	$0.00072

Measured 9d ago against content hash cbbf387d0467, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kaizen 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.

dstoic/skills/kaizen/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kaizen — Friction Capture

One-shot friction log. Capture, confirm, resume. Speed is the point.

Usage

/kaizen <target> <note>

Both required. If either missing → respond ⚠️ Usage: /kaizen <target> <note> and stop.

Behavior

Single Bash call. Slugify target (lowercase, ./ → -), append one JSON line, count, respond:

SLUG=$(echo "<target>" | tr '[:upper:]' '[:lower:]' | tr ' ./' '---')
DIR=/praxis/thinking/kaizen
mkdir -p "$DIR"
FILE="$DIR/$SLUG.jsonl"
NOTE_JSON=$(printf '%s' "<note>" | python3 -c 'import json,sys;print(json.dumps(sys.stdin.read()))')
printf '{"ts":"%s","cwd":"%s","note":%s}\n' "$(date -Iseconds)" "$(pwd)" "$NOTE_JSON" >> "$FILE"
wc -l < "$FILE"

Then respond: 🏷 kaizen:<target> logged (total: N) — thanks and resume prior conversation immediately. No commentary, no analysis, no reformulation.

Use python3 json.dumps for escaping — never hand-roll JSON.

Reserved targets

Target	Meaning
`praxis`	Top-level meta (workflow, methodology, portfolio)
`claude.md`	Instruction drift in any CLAUDE.md. All levels collapse to `claude-md.jsonl`; disambiguate via `cwd` field at review time
`self`	Note to future-self about personal workflow habits (distinct from `introspect/self.md` identity profile)
`<skill-name>`	Friction with a specific skill — use real name, not `lazy-*` prefix

Free-form otherwise; conventions unenforced.

Examples

/kaizen troubleshoot "asks same diagnostic twice in a row"
/kaizen claude.md "git commit rules ambiguous on scope field"
/kaizen convert-pdf "OCR re-runs on cached pages"
/kaizen convert-pdf "VLM mode is great for scanned docs"
/kaizen self "forgot to check benchmarks/inventory.yaml before starting"

Praise and friction share the bucket — natural language carries the sign. No type field, no --priority, no --undo, no auto-dedupe (repeats = valid intensity signal). Manual jsonl edit if needed.

Key rules

Note required. Missing note = useless for clustering.
After-only. Works after a skill returns, not mid-skill.
Verbatim storage. No cleanup, categorization, or reformulation.
One-line response. Never comment on note content. Resume immediately.

Read the full file on GitHub · 67 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.

9d ago First seen · 67 lines · 102 tokens per session scan A cbbf387d0467

Subscribe to this mod's changes

kaizen is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 723 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 2026-08-30.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

kaizen