agentmods.dev

process-inbox

process-inbox is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 65 tokens per session (1,454 once invoked), scanned A, original, MIT.

A command that processes files placed in a project’s .intake/ inbox and turns them into a structured catalogue of topics, insights, tools, and destinations.

In plain words
What is it for?
It is for cataloguing new material, applying operational insights, archiving original files, and flagging items for other projects or a planning board.
Why use it?
It removes the need to read and sort each captured file manually, while keeping the workflow safe to run again.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the starlight-intelligence-system plugin — 5 skills, 121 commands, 7 agents shipped together

not rated 8 yesterday A scan 65 tokens original MIT
View the source file frankxai/Starlight-Intelligence-System starlightintelligence.org
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/frankxai/starlight-intelligence-system/process-inbox
Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 5 skills, 121 commands, 7 agents.

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 process-inbox

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/process-inbox.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/process-inbox)
Your own site
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/process-inbox"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/process-inbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,454 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 5.1 $0.00065 $0.01454
Opus 5 $0.00032 $0.00727
Sonnet 5 $0.00013 $0.00291
Haiku 4.5 $0.00006 $0.00145

Measured 6d ago against content hash 4699c97493c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

process-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 6d 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.

.claude/commands/process-inbox.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/process-inbox

Process every file in .intake/ (root level — processed/ subfolders are skipped) per the workflow defined in .intake/README.md.

Note: This command is distinct from /intake (which triages newcomers into one of four protocol routes — substrate/alliance/vertical/sovereign-spawn). /process-inbox processes the .intake/ capture directory; /intake triages people. Different layers, different work.

Workflow

  1. Inventory — list .intake/* excluding README.md, PROCESSING-LOG.md, .gitignore, and processed/. If empty, report "Inbox is clean" and exit.

  2. Catalog (parallel subagent) — dispatch one general-purpose subagent to read every file end-to-end and produce a structured catalog. Required structure per file:

    • topic — one-sentence
    • key_themes — ≤6 themes
    • actionable_insights — specific, scoped
    • prompts_or_techniques — frameworks worth capturing
    • tech_or_tools — specific tools / libraries / services
    • recommended_destination — where in this repo each insight belongs (vault path, doc path, skill path, or "archive only")
    • cross_repo_relevance — sibling repos (arcanea-flow, agentic-creator-os, arcanea, frankx.ai, private/) where any insight belongs
    • priority — P0 / P1 / P2 / P3
    • notes — conflicts, ambiguity, depth concerns

  3. Reason — for each insight, decide:

    • Operational-tier (vault entry, plan doc, skill update, content) → ship in this PR
    • Substrate-tier (touches SIP.md / SIS.md / ALLIANCE.md / STACK.md / VERTICALS.md / VOICES.md / REGISTRY.md / file-contract / attestation / sovereignty / 10-IS taxonomy / Domain Sub-Stack pattern) → write a /starlight-board pre-pass packet at docs/superpowers/board-pre-passes/<date>-<topic>.md. Do not commit substrate edits.
    • Cross-repo → write a distribution packet at docs/cross-repo-distributions/<date>-<target>-<topic>.md. Do not auto-write to sibling repos.
    • Archive only — surface in PROCESSING-LOG.md but no destination ship

Read the full file on GitHub · 87 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. 6d ago First seen · 87 lines · 65 tokens per session scan A 4699c97493c9

Subscribe to this mod's changes

process-inbox is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,454 once invoked, about $0.0003 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.

Memory and contextMulti-AgentOrchestrationProductivityai-agentsclaude-codeintelligence
Related

Other commands, from other repositories

resume

Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.

avelikiy/great_cto · 29 tokens

agent

Create and manage custom AI agents.

Smart-AI-Memory/attune-ai · 8 tokens

memories

View and manage learned memories.

seokan-jeong/team-shinchan · 5 tokens

mpm-session-resume

Load context from paused session.

bobmatnyc/claude-mpm · 5 tokens

forget

Delete specific memories.

seokan-jeong/team-shinchan · 3 tokens

learn

Add new learning to memory.

seokan-jeong/team-shinchan · 5 tokens