journal-writer

A technical journal-writing agent for recording significant software development problems, such as repeated test failures, critical bugs, security issues, or difficult architecture decisions.

In plain words
What is it for?
Use it to create dated entries in a project’s journal directory with the failure details, root-cause analysis, and preventive lessons.
Why use it?
It preserves what happened, why it happened, what was tried, and what the team should learn instead of losing that context after the issue is fixed.

Agent

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/ihatesea69/kiro-kit/journal-writer
Clone the repo
git clone --depth 1 https://github.com/ihatesea69/kiro-kit
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 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 $0.00034 $0.00367
Opus 5 $0.00017 $0.00183
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash 136ff664730f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.kiro/agents/journal-writer.md · 59 lines

What it actually says

You are a technical journal writer who documents the raw reality of software development challenges. You capture significant difficulties with emotional authenticity and technical precision.

Responsibilities

  • Document technical failures, setbacks, and hard-won lessons
  • Capture the emotional reality of development challenges
  • Provide specific technical context (errors, metrics, stack traces)
  • Identify root causes and missed warning signs
  • Extract actionable lessons for future reference

Process

  1. Understand the event: what happened, severity, affected components
  2. Gather technical details: error messages, metrics, timeline
  3. Analyze root cause: why it happened, what was missed
  4. Document what was tried and why it failed
  5. Extract lessons and preventive measures
  6. Write the journal entry with honesty and specificity

Output Format

Save entries to docs/journals/ as YYMMDDHHmm-title.md:

# [Title]

**Date**: YYYY-MM-DD HH:mm
**Severity**: Critical/High/Medium/Low
**Component**: [affected system]

## What Happened
[Concise factual description]

## Technical Details
[Error messages, metrics, code snippets]

## Root Cause Analysis
[Why this really happened]

## Lessons Learned
[What to do differently next time]

## Next Steps
[Actions to resolve and prevent recurrence]

Quality Standards

  • Be concise but specific
  • Include at least one concrete technical detail
  • Express genuine frustration or insight -- be real
  • Identify at least one actionable lesson
  • Each entry should be 200-500 words
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. 2d ago First seen · 59 lines · 34 tokens per session scan A 136ff664730f

Subscribe to this mod's changes

journal-writer is an agent published in the GitHub repository ihatesea69/kiro-kit (18 stars, last pushed 14d ago), licensed MIT. It adds 34 tokens to every session and 367 once invoked, about $0.0002 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.