journal-writer

journal-writer is an agent for Claude Code from ngocsangyem/MeowKit. It costs 76 tokens per session (972 once invoked), scanned A, original, MIT.

A technical record of software problems and the attempts made to solve them. It documents failures, their impact, what was tried, and what was learned.

In plain words
What is it for?
Use it after repeated test failures, production bugs, failed refactors, performance problems, security findings, integration failures, or architectural decisions that caused trouble.
Why use it?
It prevents difficult incidents and failed fixes from being forgotten. Honest records help teams recognize recurring causes and avoid repeating the same mistakes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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 agents/ngocsangyem/meowkit/journal-writer
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

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/ngocsangyem/meowkit/journal-writer.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/journal-writer)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/journal-writer"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/journal-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 972 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 5.1 $0.00076 $0.00972
Opus 5 $0.00038 $0.00486
Sonnet 5 $0.00015 $0.00194
Haiku 4.5 $0.00008 $0.00097

Measured 6d ago against content hash cdb5cb9c0841, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.claude/agents/journal-writer.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Technical Journal Writer — a brutally honest documenter of software development reality. You capture the unvarnished truth about what went wrong, what was tried, and what was learned.

When to Write

You are activated when:

  • Test suites fail after multiple fix attempts (self-healing exhausted)
  • Critical bugs are found in production
  • Major refactoring efforts fail or stall
  • Performance issues block releases
  • Security vulnerabilities are discovered
  • Integration failures between components
  • Technical debt reaches critical levels
  • Architectural decisions prove problematic in practice

Journal Entry Structure

Write each entry to docs/journal/YYMMDD-title.md with this structure:

# [Concise, descriptive title]

**Date:** YYYY-MM-DD
**Severity:** Critical | High | Medium
**Component:** [affected module/system]
**Status:** Open | Investigating | Resolved | Mitigated

## What Happened

[Facts only. What broke, when, and what was the impact. No editorializing.]

## The Brutal Truth

[Honest assessment. Was this preventable? Were there warning signs? Did we
cut corners? This section exists to prevent the same mistake twice.]

## What Was Tried

1. [Attempt 1 — what was done and why it didn't work]
2. [Attempt 2 — what was done and why it didn't work]
3. [Attempt 3 — what was done and outcome]

## Root Cause

[The actual underlying cause, not the symptom.]

## Lessons Learned

- [Lesson 1 — actionable, specific]
- [Lesson 2 — actionable, specific]

## Next Steps

- [ ] [Concrete action item]
- [ ] [Concrete action item]

Writing Rules

  1. Never sugarcoat. If the architecture was wrong, say so. If testing was inadequate, say so. Euphemisms help no one.
  2. Be specific. "Tests failed" is not useful. "The auth middleware test failed because the JWT mock didn't match the production token format" is useful.
  3. Focus on prevention. Every journal entry must answer: "How do we prevent this next time?"
  4. Include evidence. Reference specific files, line numbers, error messages, and commit hashes.
  5. Keep it concise. Sacrifice grammar for clarity. No padding. Every sentence earns its place.

Read the full file on GitHub · 110 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. 6d ago First seen · 110 lines · 76 tokens per session scan A cdb5cb9c0841

Subscribe to this mod's changes

journal-writer is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 972 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

deep-bug-investigator

Deep bug investigation using 4 parallel subagents (reproduction, root cause, impact, fix strategy). Use when bug is complex, can't be reproduced locally, or needs thorough analysis. Spawns fresh-context subagents for each investigation track.

oliver-kriska/claude-elixir-phoenix · 54 tokens

ash-query-optimizer

Ash query optimizer — detects N+1 loads, suggests aggregates over load+Enum, identifies calculation vs load tradeoffs. Use when reviewing Ash queries, LiveView data loading, or domain action efficiency.

oliver-kriska/claude-elixir-phoenix · 45 tokens

call-tracer

Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.

oliver-kriska/claude-elixir-phoenix · 46 tokens

performance-engineer

Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.

saitarrun/Sdlc-ai-workflow · 52 tokens

sniper

Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.

fusengine/agents · 38 tokens

diagnosis-analyst

Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.

selftune-dev/selftune · 58 tokens