Borrowing it
Nothing to install: this file belongs to tatargabor/set-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tatargabor/set-core/main/.claude/commands/set/inbox.mdgit clone --depth 1 https://github.com/tatargabor/set-coreWrote 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/tatargabor/set-core/inbox)<a href="https://agentmods.dev/commands/tatargabor/set-core/inbox"><img src="https://agentmods.dev/badge/commands/tatargabor/set-core/inbox.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 5.1 | $0.00000 | $0.00371 |
| Opus 5 | $0.00000 | $0.00186 |
| Sonnet 5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
inbox 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 today.
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.
What it actually says
Read incoming messages directed to this agent.
Usage: /set:inbox or /set:inbox --all
What to do:
-
Find the project's
.set-controlworktree path:- Get the current project from
~/.config/set-core/projects.json - The control worktree is at
<project_path>/.set-control
- Get the current project from
-
Read messages using the CLI:
set-control-chat --path <project_path> --json read -
Parse the JSON output and filter messages:
- Show messages addressed to the current member/worktree
- By default, show only unread messages (newer than last read timestamp)
- With
--all, show all messages
-
Get the current member name:
# Member name format: <git-user>@<hostname> git config user.name # lowercase, spaces->hyphens hostname -s # lowercase -
Display messages in chronological order:
INBOX (3 unread messages) [2026-02-08 10:30:15] tg@linux: Can you review the auth changes? [2026-02-08 10:45:22] peter@laptop: LGTM, merging now [2026-02-08 11:00:01] tg@linux: BUG: Start button doesn't work Steps: 1. Click start Expected: Game starts Actual: Nothing happens -
If no messages: output "No unread messages"
-
After displaying, suggest replying: "Reply with
/set:msg <sender> <message>"
ARGUMENTS: $ARGUMENTS
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.
- today First seen · 45 lines · 0 tokens per session scan A 6d7c4a2187c4
inbox is a command published in the GitHub repository tatargabor/set-core (35 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 371 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 2026-09-06.
Other commands, from other repositories
hatch3r-workflow
Guided development lifecycle with 4 phases (Analyze, Plan, Implement, Review) and scale-adaptive Quick Mode for small tasks; --plan-file executes an approved plan document without re-deriving it.
hatch3r-incident-response
Drive a live production incident through a structured lifecycle -- triage + topology, bounded-autonomy mitigation, stakeholder communication, then a blameless post-mortem with runbook -- via delegated sub-agents.
optimize
Show TokenJam's savings/optimize report — where quota is going and what's recoverable. Equivalent to running tj optimize.
doctor
Run TokenJam's health check — config, ingest endpoint, and storage. Equivalent to running tj doctor.
manager
CRUD command router for managing SYNAPSE domains, rules, and star-commands.
greet
Generate contextual agent greeting using GreetingBuilder infrastructure.