process-daily

A command for cleaning up voice-to-text entries in a vault's daily note. It reviews transcription corrections, improves prose, and can suggest useful notes to extract.

In plain words
What is it for?
Use it inside a vault to load its rules, find today's note, correct transcription errors, preview edits, restructure the note, and optionally suggest extractions.
Why use it?
It turns rough spoken text into a clearer daily record while showing changes for confirmation before applying them.

Command

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/technicalpickles/pickled-claude-plugins/process-daily
Clone the repo
git clone --depth 1 https://github.com/technicalpickles/pickled-claude-plugins
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 974 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 $0.00008 $0.00974
Opus 5 $0.00004 $0.00487
Sonnet 5 $0.00002 $0.00195
Haiku 4.5 $0.00001 $0.00097

Measured 2d ago against content hash 36d4babcd606, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-daily 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.

plugins/second-brain/commands/process-daily.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process Daily Note

Clean up voice transcriptions in a daily note. Works in phases with confirmation between each.

Prerequisite: Vault Context Check

This command only works inside a vault.

Check if current directory is a vault:

ls -d .obsidian 2>/dev/null

If .obsidian/ not found in current directory or parents:

⚠ /second-brain:process-daily only works inside a vault.

You're currently in: {cwd}

Options:
1. Open your vault via symlink: ~/.claude/vaults/{name}
2. Use /second-brain:insight to capture from here
3. devlog captures notable moments automatically — nothing to invoke

Stop execution - do not continue.

Overview (when in vault)

  1. Load context (daily note, glossary, vault conventions)
  2. Identify & confirm transcription corrections (batched by category)
  3. Clean prose (preview before applying)
  4. Restructure to daily note template (preview before applying)
  5. Suggest extractions (optional)

Phase 1: Load Context

Step 1.1: Read Vault CLAUDE.md

Read CLAUDE.md at vault root for:

  • Daily note location
  • Template reference
  • Structure conventions

Step 1.2: Find the Daily Note

Get the daily note path using sb:

npx @techpickles/sb daily path

If argument provided: Pass the date to sb:

npx @techpickles/sb daily path --date "{YYYY-MM-DD}"

sb returns the full path to the daily note based on .obsidian config.

If file doesn't exist, inform user and stop.

Step 1.3: Load Glossary

Read Glossary.md if it exists at vault root.

Parse correction mappings by category.

Step 1.4: Assess Content

Read daily note. Report:

Loaded: Fleeting/2026-01-21.md
Glossary: Found ({N} known corrections)
Content: ~{N} words, {structured|unstructured}

Ready to process. Continue? [Yes] [Cancel]

Phase 2: Identify & Confirm Corrections

Present corrections in batches by category:

### Tools & Software (Batch 1 of 4)

| # | Found | → Correction | Context |
|---|-------|--------------|---------|
| 1 | me's | mise | "started using me's" |
| 2 | Claude MT | CLAUDE.md | "added Claude MT" |

✓ Accept all | Enter numbers to reject | ? for more context

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 8 tokens per session scan A 36d4babcd606

Subscribe to this mod's changes

process-daily is a command published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed 5d ago), licensed MIT. It adds 8 tokens to every session and 974 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.