A project setup command for creating the files and settings needed to record work as phases. It asks for a language, model and context size, project details, and a colour palette.

Use it when starting a project or when the project's logging folder is missing.

It removes the manual work of preparing a logging folder before you start tracking project progress.

init — Skill for Claude Code by lemon-etvibe

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 lemon-etvibe/prompt-vault --skill init

Clone the repo

git clone --depth 1 https://github.com/lemon-etvibe/prompt-vault

Made for: Claude Code.

Or install prompt-vault, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 3 hooks.

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/lemon-etvibe/prompt-vault/init/github.svg)](https://agentmods.dev/skills/lemon-etvibe/prompt-vault/init)

Your own site

<a href="https://agentmods.dev/skills/lemon-etvibe/prompt-vault/init"><img src="https://agentmods.dev/badge/skills/lemon-etvibe/prompt-vault/init/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/lemon-etvibe/prompt-vault/init"><img src="https://agentmods.dev/badge/skills/lemon-etvibe/prompt-vault/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 861 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 3 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.00861
Opus 5	$0.00026	$0.00430
Sonnet 5	$0.00010	$0.00172
Haiku 4.5	$0.00005	$0.00086

Measured 8d ago against content hash 777092240357, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

init scanned grade C with 3 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 8d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s -X POST http://colormind.io/api/ -d '{"model":"default"}'

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

PLUGIN_ROOT=$(find ~/.claude/plugins -name "init.sh" -path "*/prompt-vault/scripts/*" 2>/dev/null | head -1 | sed 's|/scripts/init.sh$||')

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://colormind.io/api/ -d '{"model":"default"}'

skills/init/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up the prompt-vault logging environment for a project. This skill collects user preferences, then delegates all file creation to init.sh.

Step 0: Locate the plugin root

Find the init.sh script path:

PLUGIN_ROOT=$(find ~/.claude/plugins -name "init.sh" -path "*/prompt-vault/scripts/*" 2>/dev/null | head -1 | sed 's|/scripts/init.sh$||')
echo "PLUGIN_ROOT=${PLUGIN_ROOT}"

If PLUGIN_ROOT is empty, stop and tell the user the plugin is not installed properly.

Step 1: Language

Check $ARGUMENTS:

en → LANG=en, skip asking
ko → LANG=ko, skip asking

empty → ask:

Choose language / 언어 선택:
[1] English (default)  [2] 한국어

Step 2: Model & Context

Ask which model/plan is in use:

Model	context_tokens	warn_bytes
Opus 4.6 / Sonnet 4.5 / Haiku 4.5 (200K)	200000	640000
Extended (1M)	1000000	3200000

Step 3: Project Metadata

project_name: default = current directory name
project_description: one-line description (default: empty)

Step 4: Palette

Generate a 5-color palette:

# Primary: colormind.io API (free, no key)
curl -s -X POST http://colormind.io/api/ -d '{"model":"default"}'
# Convert RGB → HEX array

# Fallback: random from curated palettes
jq -r ".[$RANDOM_INDEX]" "${PLUGIN_ROOT}/data/palettes.json"

Step 5: Auto-Logging

Ask:

en: "Enable auto-logging? (Turn-count based automatic recording via Stop hook)"
ko: "자동 로깅을 활성화할까요? (Stop 훅에서 턴 수 기반 자동 기록)"

If yes → auto_log=true, turn_threshold=3 If no → auto_log=false

Step 6: Run init.sh

MUST execute this command — this is the core of initialization:

bash "${PLUGIN_ROOT}/scripts/init.sh" \
  "$PWD" \
  "<LANG>" \
  "<MODEL_ID>" \
  "<CONTEXT_TOKENS>" \
  "<WARN_BYTES>" \
  "<PROJECT_NAME>" \
  "<PROJECT_DESC>" \
  '<PALETTE_JSON>' \
  "<AUTO_LOG_ENABLED>" \
  "<TURN_THRESHOLD>"

The script creates ALL required files:

.local/logs/ directory
.local/logs/.config (NOT config.json — the file MUST be named .config)
.local/logs/_index.md
.gitignore entry
CLAUDE.md logging protocol section

Read the full file on GitHub · 111 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.

8d ago First seen · 111 lines · 52 tokens per session scan C 777092240357

Subscribe to this mod's changes

init is a skill published in the GitHub repository lemon-etvibe/prompt-vault (2 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 861 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 3 findings (sends data to an external url, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claude claude-code-plugin developer-tools logging plugin prompt

init

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Sends data to an external URLmediumData exfiltration

Reads agent configuration directoriesmediumAgent snooping

Makes network callslowCapability

How it starts

Step 0: Locate the plugin root

Step 1: Language

Step 2: Model & Context

Step 3: Project Metadata

Step 4: Palette

Step 5: Auto-Logging

Step 6: Run init.sh

What this file has done since we first saw it

Other skills, from other repositories

brainstorm

ship

sitrep

fastapi

docs

memory