overview

overview is a command for coding agents from gf-labs/claude-toolbox. It costs 47 tokens per session (798 once invoked), scanned A, original, MIT.

A command that produces a project overview for Claude Code, including repository state, recent commits, pending work, active plans, and available project information.

In plain words
What is it for?
Use it at the start of a session or when prioritising work in a repository.
Why use it?
It collects the context needed to decide what to work on next instead of relying on scattered files or memory. It can also show when supporting tools such as TaskWarrior are unavailable.

Command

Part of the tools plugin — 2 skills, 13 commands, 5 agents, 4 hooks 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/gf-labs/claude-toolbox/overview
Clone the repo
git clone --depth 1 https://github.com/gf-labs/claude-toolbox

Or install tools, the plugin that ships this one along with the rest of its 2 skills, 13 commands, 5 agents, 4 hooks.

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 overview

README.md
[![agentmods](https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/overview.svg)](https://agentmods.dev/commands/gf-labs/claude-toolbox/overview)
Your own site
<a href="https://agentmods.dev/commands/gf-labs/claude-toolbox/overview"><img src="https://agentmods.dev/badge/commands/gf-labs/claude-toolbox/overview.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 798 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 $0.00047 $0.00798
Opus 5 $0.00023 $0.00399
Sonnet 5 $0.00009 $0.00160
Haiku 4.5 $0.00005 $0.00080

Measured 4d ago against content hash 2918196bd858, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

overview 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.

commands/overview.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collect context

Run all commands now before producing output.

Scope + date:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_scope.py
date +%Y-%m-%d

Git state:

echo "BRANCH:" && (git branch -vv 2>/dev/null | head -3 || echo "not a git repo")
echo "UNCOMMITTED:" && (git status --short 2>/dev/null | wc -l | tr -d ' ')
echo "UNPUSHED:" && (git log @{u}.. --oneline 2>/dev/null | wc -l | tr -d ' ')
echo "LOG:" && git log --oneline -8 2>/dev/null
echo "CHANGED_FILES:" && git status --short 2>/dev/null

Backlog (TaskWarrior):

TW_PROJECT=$(python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_slug.py)
task rc.verbose=nothing project:${TW_PROJECT} limit:5 list 2>/dev/null || echo "(TaskWarrior unavailable)"

Inventory:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-inventory.py 2>/dev/null || echo "(unavailable)"

Active plans (this project):

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-plans.py 2>/dev/null

Session log:

python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/collect-session-log.py 2>/dev/null

Project metadata (if plugin):

python3 -c "import json; d=json.load(open('.claude-plugin/plugin.json')); print('plugin v' + d['version'])" 2>/dev/null || true

Your role

Read all collected context and produce a PM-style overview for the current project. Be specific and direct — not a git log dump, not a backlog recitation.

Flag any discrepancies between TaskWarrior tasks, active plans, and actual git state. Trust git over planning docs when they conflict.

When building the Sequencing section: weight session log recency — if the last session log entry has an open Resume: or Open threads: line, surface that as the top "Now" item. Cross-reference the session log against backlog items to identify what's already in motion vs. cold-start work.


Output format

[repo name] — [version if plugin] — [date]

Current state — one honest sentence.

Recent work — what shipped in the last few sessions (git log + session log). 3–5 bullets, outcomes not mechanics.

Read the full file on GitHub · 94 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 · 94 lines · 0 tokens per session scan A 2918196bd858

Subscribe to this mod's changes

overview is a command published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 798 once invoked, about $0.0002 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.