digest

digest is a command for Claude Code from gkaria/vibe-learn. It costs 24 tokens per session (1,445 once invoked), scanned B, original, MIT.

A session-learning report generator that reviews what was built, the decisions made, coding patterns used, and topics worth studying. It can also connect the report with earlier project sessions saved in an Obsidian note vault.

In plain words
What is it for?
Use it after a coding session to create a structured study report or recall earlier work on the same project from Obsidian notes.
Why use it?
It turns a long coding session into a readable record, so important choices and lessons are not lost. It also helps relate current work to previous sessions.

Command for Claude Code

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/gkaria/vibe-learn/digest
Clone the repo
git clone --depth 1 https://github.com/gkaria/vibe-learn

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 digest

README.md
[![agentmods](https://agentmods.dev/badge/commands/gkaria/vibe-learn/digest.svg)](https://agentmods.dev/commands/gkaria/vibe-learn/digest)
Your own site
<a href="https://agentmods.dev/commands/gkaria/vibe-learn/digest"><img src="https://agentmods.dev/badge/commands/gkaria/vibe-learn/digest.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,445 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00024 $0.01445
Opus 5 $0.00012 $0.00723
Sonnet 5 $0.00005 $0.00289
Haiku 4.5 $0.00002 $0.00145

Measured 4d ago against content hash f6d332f7d9a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

digest scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Ledger update (all modes):** after generating the digest, record each concept this session introduced via the knowledge helper, one call per concept: `bash ~/.vibe-learn/scripts/knowledge.sh touch <kebab-case-name> --l
.claude/commands/digest.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read .vibe-learn/session-log.jsonl (the full log). Read any relevant source files to understand what was built.

Parse $ARGUMENTS to determine the mode:


Mode: obsidian:recall

If $ARGUMENTS is obsidian:recall:

Step 1 — Load config: Check .vibe-learn/obsidian.json first, then ~/.vibe-learn/obsidian.json. If neither exists, run the same config setup flow as /digest obsidian (ask vault path, subfolder, global vs project save location) before proceeding.

Step 2 — Search for previous sessions on this project:

  • Determine the project name from the working directory (last path component).
  • Search <vault_path>/<subfolder>/ for markdown files where:
    • The frontmatter project field matches the project name, OR
    • The filename contains the project name
  • Read the most recent matching files (up to 5), ordered by date frontmatter descending.

Step 3 — Generate the enriched digest:

Produce the full structured digest as normal (What Was Built, Key Decisions, Patterns Used, Things to Study, Session Activity), then append a "Connections to Previous Work" section:

## Connections to Previous Work

- How this session builds on or continues prior work
- Recurring patterns seen across sessions
- Unchecked "Things to Study" items from past sessions relevant to what was just built
- Progression of understanding (e.g., "You first set up JWT auth on March 2nd, this session extends it with refresh tokens")

If no previous session notes are found for this project, note that in the section and omit the connections content.

Step 4 — Write the enriched note to the vault (same write behavior as /digest obsidian below).


Mode: obsidian

If $ARGUMENTS is obsidian:

Step 1 — Load config: Check .vibe-learn/obsidian.json, then ~/.vibe-learn/obsidian.json.

If no config is found:

  • Ask the user: "What is the path to your Obsidian vault? (e.g. /Users/me/MyVault)"
  • Ask: "Which subfolder should vibe-learn notes go in? (default: Development/Sessions)"
  • Ask: "Save this config globally for all projects (~/.vibe-learn/obsidian.json) or just for this project (.vibe-learn/obsidian.json)? [global/project, default: global]"
  • Write the config to the chosen location (creating the directory with mkdir -p if needed):

Read the full file on GitHub · 162 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. 4d ago First seen · 162 lines · 24 tokens per session scan B f6d332f7d9a5

Subscribe to this mod's changes

digest is a command published in the GitHub repository gkaria/vibe-learn (54 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 1,445 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.