Ein Befehl für eine morgendliche Zusammenfassung des aktuellen Arbeitsstands. Er liest vorhandene Notizen, Projekte und Personeninformationen und sucht zusätzlich nach jüngeren Aktivitäten.

Für einen schnellen Überblick über die letzten Sitzungen, offene Projekte, Entscheidungen und kürzlich festgehaltene Fortschritte.

Du musst nicht mehrere Dateien und frühere Einträge einzeln durchsuchen, um wieder in ein Projekt hineinzukommen.

briefing — Command for Claude Code by tstockham96/claw-kit

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/tstockham96/claw-kit

agentmods

npx agentmods add commands/tstockham96/claw-kit/briefing

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/tstockham96/claw-kit/briefing/github.svg)](https://agentmods.dev/commands/tstockham96/claw-kit/briefing)

Your own site

<a href="https://agentmods.dev/commands/tstockham96/claw-kit/briefing"><img src="https://agentmods.dev/badge/commands/tstockham96/claw-kit/briefing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/tstockham96/claw-kit/briefing"><img src="https://agentmods.dev/badge/commands/tstockham96/claw-kit/briefing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 803 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00803
Opus 5.5	$0.00000	$0.00321
Sonnet 5.5	$0.00000	$0.00161
Haiku 4.5	$0.00000	$0.00080

Measured 1mo ago against content hash 744959b3209a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

briefing 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 1mo 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.

kit/commands/briefing.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/briefing

Morning summary. Show the user where things stand so they can pick up where they left off. This is the "catch me up" command.

Instructions

Step 1: Gather Context

Read the following files directly (skip any that don't exist):

memory/journal/YYYY-MM-DD.md -- today's date (may not exist if it's early in the day)
memory/journal/YYYY-MM-DD.md -- yesterday's date
memory/journal/YYYY-MM-DD.md -- two days ago (for additional context if yesterday is thin)
memory/projects/_index.md -- active projects
memory/people/_index.md -- known people for context
memory/user.md -- for timezone and personal context

Step 2: Search for Recent Activity

Use the search engine to find recent activity, decisions, and context that the direct file reads might miss:

cd kit/search && npx tsx src/cli.ts search "recent session work progress" --limit 10 --memory-path ../memory

Also search for any active project names found in projects/_index.md to surface recent project-specific context:

cd kit/search && npx tsx src/cli.ts search "[project name]" --limit 5 --memory-path ../memory

Scan the decisions directory for any files from the last 7 days:

memory/decisions/ -- look for files with recent dates in their filenames

Step 3: Search for People in Context

If any people were mentioned in recent journal entries or search results, search for additional context:

cd kit/search && npx tsx src/cli.ts search "[person name]" --limit 3 --memory-path ../memory

Step 4: Build the Briefing

Present a clean, scannable summary using this format:

## Good morning. Here's where we left off.

### Last Session
[Summarize the most recent journal entry. What was worked on? What was the state when the session ended? Any open threads?]
[Include citations: (Source: journal/YYYY-MM-DD.md#line)]

[If no recent journal entries exist: "No recent session history. This might be our first conversation, or sessions haven't been logged yet."]

### Active Projects
[For each project in _index.md, show: name, current status, and any recent activity from journal entries or search results. Highlight anything that seems urgent or time-sensitive.]
[Include citations to project files and journal entries.]

[If no projects: "No projects being tracked yet."]

### Recent Decisions
[List any decisions from the last 7 days with a one-line summary of each. Include citation to decision file.]

[If none: skip this section entirely.]

### Open Threads
[Extract any unresolved questions, pending items, or "next steps" mentioned in recent journal entries or search results. These are things that might need attention today.]

[If none: skip this section entirely.]

### People in Context
[If any people were mentioned in recent journal entries, note them briefly with their role/relationship. Include citations.]

[If none: skip this section entirely.]

Read the full file on GitHub · 85 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.

1mo ago First seen · 85 lines · 0 tokens per session scan A 744959b3209a

Subscribe to this mod's changes

briefing is a command published in the GitHub repository tstockham96/claw-kit (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 803 tokens. 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.

Claude Code Productivity ai-agent ai-memory anthropic claude openclaw

orchestrate

Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.

egorfedorov/claude-context-optimizer · 0 tokens

briefing