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.
npx agentmods add commands/pghh84/claude-layered-learning/diarygit clone --depth 1 https://github.com/PGHH84/claude-layered-learningWrote 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.
[](https://agentmods.dev/commands/pghh84/claude-layered-learning/diary)<a href="https://agentmods.dev/commands/pghh84/claude-layered-learning/diary"><img src="https://agentmods.dev/badge/commands/pghh84/claude-layered-learning/diary.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00009 | $0.01050 |
| Opus 5 | $0.00005 | $0.00525 |
| Sonnet 5 | $0.00002 | $0.00210 |
| Haiku 4.5 | $0.00001 | $0.00105 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Diary Entry
Capture a structured diary entry documenting the current Claude Code session.
This entry is raw material for /reflect to mine later for cross-session
patterns. It is not analyzed or routed here.
Approach: Context-First Strategy
Primary method (use this first): Reflect on the conversation history loaded in this session. You have access to:
- 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 such as exact tool counts or timestamps
- the user explicitly requests detailed session analysis
Runtime Paths
- diary output:
~/.claude/memory/diary/YYYY-MM-DD-<project-slug>-session-N.md - project memory that may already exist:
~/.claude/projects/<slug>/memory/MEMORY.md
Path-To-Slug Transform
Use this exact transform so /diary, /reflect, wrap-up, and the PreCompact
hook agree on project identity:
- If inside a git repository, resolve the canonical project root with
git rev-parse --show-toplevel. - If that repo root contains
/.worktrees/, strip the/.worktrees/<name>suffix and use the parent repo path as the canonical project root. - Otherwise, if not inside a git repository, use the canonical absolute working directory.
- Resolve symlinks before deriving the slug.
- Replace every
/in the canonical absolute path with-.
Session Number Source of Truth
Use one source of truth for the session number so wrap-up and standalone
/diary do not diverge.
- preferred source of truth:
~/.claude/projects/<slug>/memory/MEMORY.md - fallback: scan matching diary files for the same project and date only when
MEMORY.mdis missing or uninitialized - if
wrap-upalready updatedMEMORY.md, reuse that session number instead of incrementing again - include a
Session IDline only when a runtime session identifier is actually available
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.
- 4d ago First seen · 166 lines · 9 tokens per session scan A bd117a28f22a
diary is a command published in the GitHub repository PGHH84/claude-layered-learning (2 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 1,050 once invoked, about $0.0000 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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.