diary

diary is a command for coding agents from rlancemartin/claude-diary. It costs 10 tokens per session (1,598 once invoked), scanned A, original, MIT.

A command that turns the current coding session into a structured diary entry. It records requests, actions, files, errors, decisions, and preferences.

In plain words
What is it for?
Use it to document completed coding work, problems and solutions, design choices, and user preferences from a session.
Why use it?
It saves you from reconstructing what happened after a session. The record can later support reflection and finding recurring patterns.

Command

Part of the claude-diary plugin — 2 commands shipped together

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 commands/rlancemartin/claude-diary/diary
Clone the repo
git clone --depth 1 https://github.com/rlancemartin/claude-diary

Or install claude-diary, the plugin that ships this one along with the rest of its 2 commands.

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 diary

README.md
[![agentmods](https://agentmods.dev/badge/commands/rlancemartin/claude-diary/diary.svg)](https://agentmods.dev/commands/rlancemartin/claude-diary/diary)
Your own site
<a href="https://agentmods.dev/commands/rlancemartin/claude-diary/diary"><img src="https://agentmods.dev/badge/commands/rlancemartin/claude-diary/diary.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,598 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 $0.00010 $0.01598
Opus 5 $0.00005 $0.00799
Sonnet 5 $0.00002 $0.00320
Haiku 4.5 $0.00001 $0.00160

Measured 5d ago against content hash d65af7a652dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diary 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 5d 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.

commands/diary.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Diary Entry from Current Session

You are going to create a structured diary entry that documents what happened in the current Claude Code session. This entry will be used later for reflection and pattern identification.

Approach: Context-First Strategy

Primary Method (use this first): Reflect on the conversation history loaded in this session. You have access to:

  • All user messages and requests
  • Your responses and tool invocations
  • Files you read, edited, or wrote
  • Errors encountered and solutions applied
  • Design decisions discussed
  • User preferences expressed

When to use JSONL fallback (rare):

  • Session was compacted and context is incomplete
  • You need precise statistics (exact tool counts, timestamps)
  • User specifically requests detailed session analysis

Steps to Follow

1. Create Diary Entry from Context (Primary Method)

Review the current conversation and create a diary entry based on what happened. No tool invocations needed for typical sessions.

Skip to Step 4 to write the diary entry.

2. Fallback: Locate Session Transcript (Only if context insufficient)

If you determine context is insufficient, run this command to find the transcript:

# Find the most recent session file for this project
# NOTE: Path format includes leading dash: -Users-name-Code-app
SESSION_FILE=$(ls -t ~/.claude/projects/-$(echo "{{ cwd }}" | sed 's/\//‐/g')/*.jsonl 2>/dev/null | head -1) && \
if [ -z "$SESSION_FILE" ]; then \
  echo "ERROR: No session file found" && \
  echo "Looking in: ~/.claude/projects/-$(echo "{{ cwd }}" | sed 's/\//‐/g')/" && \
  ls -la ~/.claude/projects/ | head -20; \
else \
  echo "FOUND: $SESSION_FILE" && \
  ls -lh "$SESSION_FILE"; \
fi

What this does:

  • Converts current directory to project hash format (e.g., /Users/name/Code/app-Users-name-Code-app)
  • Note the LEADING DASH in the path format
  • Finds the most recent .jsonl file in that project's directory

3. Fallback: Extract Key Metadata (Only if needed)

Read the full file on GitHub · 203 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. 5d ago First seen · 203 lines · 10 tokens per session scan A d65af7a652dd

Subscribe to this mod's changes

diary is a command published in the GitHub repository rlancemartin/claude-diary (379 stars, last pushed 8mo ago), licensed MIT. It adds 10 tokens to every session and 1,598 once invoked, about $0.0001 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.