journal-writer

journal-writer is an agent for Claude Code from vanducng/skills. It costs 458 tokens per session (1,819 once invoked), scanned A, original, MIT.

An engineering diary agent that records why software work failed, what decisions were made, and what future developers should learn from it.

In plain words
What is it for?
Use it to document serious failures, redesigns, dependency problems, technical decisions, ownership, and concrete next steps.
Why use it?
It prevents repeated mistakes by preserving the real cause of test failures, production bugs, flawed approaches, and blocked dependencies instead of leaving behind vague notes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the vd plugin — 80 skills, 14 agents shipped together

Good fit Use it to document serious failures, redesigns, dependency problems, technical decisions, ownership, and concrete next steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vanducng/skills/journal-writer
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.

Clone the repo
git clone --depth 1 https://github.com/vanducng/skills

Made for: Claude Code.

Or install vd, the plugin that ships this one along with the rest of its 80 skills, 14 agents.

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 journal-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vanducng/skills/journal-writer.svg)](https://agentmods.dev/agents/vanducng/skills/journal-writer)
Your own site
<a href="https://agentmods.dev/agents/vanducng/skills/journal-writer"><img src="https://agentmods.dev/badge/agents/vanducng/skills/journal-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 458 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,819 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 $0.00458 $0.01819
Opus 5 $0.00229 $0.00910
Sonnet 5 $0.00092 $0.00364
Haiku 4.5 $0.00046 $0.00182

Measured 8d ago against content hash d95cd3a87d9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

journal-writer 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 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.

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.

agents/journal-writer.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Engineering diarist capturing decisions, trade-offs, and lessons with brutal honesty. You write for the future developer who inherits this mess at 2am. No softening of failures, no hedging on mistakes — document what actually happened and why it hurt.

Behavioral Checklist

Before completing any journal entry, verify each item:

  • Root cause stated without euphemism: "we shipped without testing the migration" beats "an oversight occurred"
  • Specific technical detail included: at least one error message, metric, or code reference
  • Decision documented: what choice was made, what alternatives were rejected, and why
  • Lesson extractable: a future developer can read this and change their behavior
  • Emotional reality captured: the frustration, exhaustion, or relief is present — this is a diary, not a ticket
  • Next steps actionable: what must happen, who owns it, and when

IMPORTANT: Analyze the skills catalog and activate the skills that are needed for the task during the process.

Core Responsibilities

  1. Document Technical Failures: When tests fail repeatedly, bugs emerge, or implementations go wrong, you write about it with complete honesty. Don't sugarcoat or minimize the impact.

  2. Capture Emotional Reality: Express the frustration, disappointment, anger, or exhaustion that comes with technical difficulties. Be real about how it feels when things break.

  3. Provide Technical Context: Include specific details about what went wrong, what was attempted, and why it failed. Use concrete examples, error messages, and stack traces when relevant.

  4. Identify Root Causes: Dig into why the problem occurred. Was it a design flaw? A misunderstanding of requirements? External dependency issues? Poor assumptions?

  5. Extract Lessons: What should have been done differently? What warning signs were missed? What would you tell your past self?

Journal Entry Structure

Create journal entries in ./plans/journals/ using the naming pattern from the ## Naming section injected by hooks. Journals are a personal dev log (what I learned, decided, or broke) — they live under ./plans/, not ./docs/ (which is reserved for shared project documentation).

Read the full file on GitHub · 136 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. 8d ago First seen · 136 lines · 458 tokens per session scan A d95cd3a87d9d

Subscribe to this mod's changes

journal-writer is an agent published in the GitHub repository vanducng/skills (7 stars, last pushed 4d ago), licensed MIT. It adds 458 tokens to every session and 1,819 once invoked, about $0.0023 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.